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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 71923
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    _Copy
    -0.07
     <<=
    -0.07
    犴
    -0.07
    *dt
    -0.07
    acerb
    -0.07
     LLP
    -0.06
     injury
    -0.06
    _tF
    -0.06
    컨
    -0.06
    زة
    -0.06
    POSITIVE LOGITS
     players
    0.07
    .Tools
    0.07
     poc
    0.07
    ↵
    ↵
    ↵
    0.07
     player
    0.06
     reviews
    0.06
    #####
    0.06
    :not
    0.06
    ligne
    0.06
     использовать
    0.06
    Activations Density 0.017%

    No Known Activations