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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    6. 76058
    Prev
    Next
    INDEX
    Explanations

    Airbag deployment

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TEE
    -0.07
    _ctx
    -0.07
     semble
    -0.07
    戋
    -0.07
     scène
    -0.07
    㺄
    -0.07
     компани
    -0.07
    stände
    -0.06
    	Point
    -0.06
    _policy
    -0.06
    POSITIVE LOGITS
    Ȃ
    0.08
    arry
    0.08
    𝗜
    0.07
     arity
    0.07
    -arrow
    0.07
    LABEL
    0.07
     Latter
    0.07
    功能性
    0.07
     unlimited
    0.07
    Ro
    0.07
    Activations Density 0.019%

    No Known Activations