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. 88242
    Prev
    Next
    INDEX
    Explanations

    chemical/molecular structures

    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
     suce
    -0.07
    副会长
    -0.07
    옜
    -0.07
    /ad
    -0.07
     самого
    -0.07
     businessmen
    -0.07
     Wooden
    -0.07
    獨立
    -0.07
    isoner
    -0.07
    .layoutControlItem
    -0.07
    POSITIVE LOGITS
    disp
    0.07
    RS
    0.07
    职场
    0.07
     text
    0.07
     overwrite
    0.07
     drains
    0.07
     ms
    0.07
     Color
    0.07
     Dustin
    0.07
     aspects
    0.07
    Activations Density 0.018%

    No Known Activations