© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 126761
    Prev
    Next
    INDEX
    Explanations

    music and trends

    np_max-act · gemini-2.0-flash

    tokens that are numeric sequences or other URL/filename-like alphanumeric ID fragments (e.g., image/file IDs).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ביצוע
    -0.08
     Chennai
    -0.07
     getConnection
    -0.07
    кой
    -0.07
    	final
    -0.07
    -0.07
    珅
    -0.07
    𝖗
    -0.07
    建成后
    -0.06
    λ
    -0.06
    POSITIVE LOGITS
     Colon
    0.08
    🔍
    0.08
     fraught
    0.07
    belt
    0.07
     loung
    0.07
     Mental
    0.07
    หลาย
    0.07
    藏着
    0.06
    打卡
    0.06
     cen
    0.06
    Activations Density 2.141%

    No Known Activations