© 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. 19-RESID-POST-AA
    11. 69057
    Prev
    Next
    INDEX
    Explanations

    asterisk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funcionários
    -0.07
    ODE
    -0.07
     errmsg
    -0.07
    优先
    -0.07
     jsonify
    -0.07
     CSL
    -0.07
    ço
    -0.07
     kości
    -0.07
    placed
    -0.07
     QLatin
    -0.06
    POSITIVE LOGITS
    Discovery
    0.07
     بدون
    0.07
    Ta
    0.07
    чист
    0.07
    .configuration
    0.07
    (cert
    0.06
    是一部
    0.06
    一带
    0.06
    +":
    0.06
    وحدة
    0.06
    Activations Density 0.000%

    No Known Activations