Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 75779
    Prev
    Next
    INDEX
    Explanations

    coding commands

    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
     Cd
    -0.07
     shot
    -0.06
     Almost
    -0.06
     restores
    -0.06
     Jos
    -0.06
     astronom
    -0.06
     kindergarten
    -0.06
     restricting
    -0.06
     Kah
    -0.06
     exploded
    -0.06
    POSITIVE LOGITS
     наз
    0.08
    <[
    0.07
    犍
    0.07
    .NewLine
    0.06
    رك
    0.06
     )(
    0.06
    reglo
    0.06
     Seahawks
    0.06
     לבח
    0.06
    Drawer
    0.06
    Activations Density 0.004%

    No Known Activations