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. 72664
    Prev
    Next
    INDEX
    Explanations

    Something said before

    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
    Rua
    -0.08
     Atari
    -0.08
     Cay
    -0.08
    road
    -0.08
    Borders
    -0.07
    -field
    -0.07
     NPC
    -0.07
    _topic
    -0.07
    进行全面
    -0.07
    سار
    -0.07
    POSITIVE LOGITS
     contrace
    0.07
     compare
    0.07
     intersects
    0.07
    堅持
    0.07
    恭喜
    0.07
     helped
    0.07
    维持
    0.07
    .ex
    0.07
     выпуск
    0.07
    」↵↵
    0.07
    Activations Density 0.044%

    No Known Activations