© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151287
    Prev
    Next
    INDEX
    Explanations

    announcements and invitations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    isters
    -0.26
    akens
    -0.26
    _consts
    -0.25
    objectId
    -0.25
    levels
    -0.25
    eners
    -0.25
     ACTIONS
    -0.25
     rowNum
    -0.25
    -bars
    -0.25
    è¿ĽæĿ¥
    -0.24
    POSITIVE LOGITS
     Boxes
    0.25
    ä¸Ĭä¸ĭ游
    0.25
     private
    0.25
     tháºŃt
    0.24
    æīĢè°ĵ
    0.24
    AD
    0.24
     ret
    0.24
     Ñģобой
    0.24
    ç»Ĩ
    0.24
     boxes
    0.24
    Activations Density 0.129%

    No Known Activations