© 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. 23-TRANSCODER-HP
    7. 25275
    Prev
    Next
    INDEX
    Explanations

    Ber

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilen
    -0.30
    èѦ
    -0.28
    >>↵↵
    -0.27
    ules
    -0.27
     pal
    -0.27
    леÑĩ
    -0.25
    stances
    -0.25
    TB
    -0.24
    arin
    -0.24
    iasm
    -0.24
    POSITIVE LOGITS
    年级
    0.24
    esto
    0.23
    第ä¸Ģå±Ĭ
    0.23
    éĽī
    0.23
    keley
    0.23
    ç«ĭãģ¡
    0.23
    ç»ıéªĮ
    0.23
     renderer
    0.22
     Maur
    0.22
    -most
    0.22
    Activations Density 0.279%

    No Known Activations