© 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. 61624
    Prev
    Next
    INDEX
    Explanations

    html attributes

    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
    pr
    -0.07
    oure
    -0.07
     sweetheart
    -0.07
    ndo
    -0.06
    .IS
    -0.06
     ServiceProvider
    -0.06
     Huffington
    -0.06
     cleansing
    -0.06
    :/
    -0.06
     przypad
    -0.06
    POSITIVE LOGITS
    妫
    0.08
     drilled
    0.08
    Cascade
    0.07
    Keith
    0.07
    Released
    0.07
    㵐
    0.07
    etrain
    0.07
    ଉ
    0.06
    传来
    0.06
    -focus
    0.06
    Activations Density 0.076%

    No Known Activations