© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 111749
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash

    user requests that start with or contain the phrase "tell me about" (the token "about" in information-asking prompts).

    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
    mina
    -0.07
    時点で
    -0.06
     Arrays
    -0.06
     segments
    -0.06
                        
    ↵
    -0.06
     stop
    -0.06
     zip
    -0.06
     Satoshi
    -0.06
    OUN
    -0.06
     trek
    -0.06
    POSITIVE LOGITS
    >{$
    0.08
    虚
    0.07
    normalize
    0.07
    一个月
    0.07
     Kiss
    0.07
     clase
    0.07
     lub
    0.07
    (room
    0.07
    ʸ
    0.07
    itchen
    0.06
    Activations Density 0.034%

    No Known Activations