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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 71413
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     thuis
    -0.07
    颞
    -0.07
     feasibility
    -0.07
    Pour
    -0.07
     matchup
    -0.06
     België
    -0.06
     hebben
    -0.06
    ք
    -0.06
    יישוב
    -0.06
    לות
    -0.06
    POSITIVE LOGITS
    借鉴
    0.07
    Injection
    0.07
    这些
    0.07
     minWidth
    0.07
    居然
    0.07
    cold
    0.07
    富力
    0.06
    -Jul
    0.06
    很明显
    0.06
    (sr
    0.06
    Activations Density 0.092%

    No Known Activations