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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 52590
    Prev
    Next
    INDEX
    Explanations

    ually

    np_max-act · gemini-2.0-flash
    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
     derive
    -0.07
    energy
    -0.07
    .push
    -0.07
    .const
    -0.07
     pos
    -0.07
    (boost
    -0.07
    verse
    -0.07
    	search
    -0.07
     ave
    -0.06
    IP
    -0.06
    POSITIVE LOGITS
     Belize
    0.08
     servings
    0.07
    开幕
    0.07
     örnek
    0.07
    惯例
    0.07
    ifth
    0.07
    /******************************************************************************↵
    0.07
    有机会
    0.07
    合适
    0.07
    を選ぶ
    0.07
    Activations Density 0.005%

    No Known Activations