© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 87476
    Prev
    Next
    INDEX
    Explanations

    leases

    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
     '|
    -0.09
    ;!
    -0.07
    ikel
    -0.07
    လ
    -0.07
    תאר
    -0.07
    fon
    -0.07
    sex
    -0.07
    ahren
    -0.07
    (";
    -0.07
    requests
    -0.07
    POSITIVE LOGITS
    =$
    0.06
     Answer
    0.06
    .proc
    0.06
    BOOST
    0.06
    _rq
    0.06
    Func
    0.06
     employ
    0.06
    붉
    0.06
    Mult
    0.06
    ached
    0.06
    Activations Density 0.059%

    No Known Activations