© 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. 12-TRANSCODER-HP
    7. 24266
    Prev
    Next
    INDEX
    Explanations

    Voyage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    baugh
    -0.34
    puted
    -0.30
    ouses
    -0.29
    uctive
    -0.28
    æľĢåIJİ
    -0.27
    ive
    -0.27
    åĮºå§Ķ
    -0.26
    (Func
    -0.26
    çĶŁåij½
    -0.26
    ç®±åŃIJ
    -0.26
    POSITIVE LOGITS
    èĩªåĪ¶
    0.27
    .dev
    0.27
    åľ©
    0.26
    isko
    0.25
    .stream
    0.24
    ",__
    0.23
    请éĢīæĭ©
    0.23
    详ç»ĨçļĦ
    0.23
    æĻĤéĸĵãĤĴ
    0.23
    _UPLOAD
    0.23
    Activations Density 0.140%

    No Known Activations