© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 71057
    Prev
    Next
    INDEX
    Explanations

    Programming/coding context

    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
    是真的
    -0.07
    CSV
    -0.07
    setUp
    -0.07
    .body
    -0.07
    欣喜
    -0.07
    毗
    -0.07
     afternoon
    -0.07
    Inform
    -0.07
     결국
    -0.07
     pues
    -0.07
    POSITIVE LOGITS
    _w
    0.07
     ##
    0.07
    input
    0.07
    usses
    0.07
    elf
    0.07
     $"
    0.07
    loop
    0.07
     Border
    0.07
    _size
    0.07
    _CONTROLLER
    0.07
    Activations Density 0.002%

    No Known Activations