© 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. 15-RESID-POST-AA
    6. 13524
    Prev
    Next
    INDEX
    Explanations

    genetic

    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
     Least
    -0.07
    remain
    -0.07
    /Core
    -0.07
    ierrez
    -0.06
     joy
    -0.06
    ulfilled
    -0.06
    .Restrict
    -0.06
    invoice
    -0.06
    (value
    -0.06
     Yield
    -0.06
    POSITIVE LOGITS
    edu
    0.08
    'al
    0.07
    esehen
    0.07
     intéressant
    0.07
    王者荣耀
    0.07
    /the
    0.07
    提前
    0.07
     forwarding
    0.07
    [C
    0.07
    on
    0.07
    Activations Density 0.009%

    No Known Activations