© 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. 14-TRANSCODER-HP
    7. 39459
    Prev
    Next
    INDEX
    Explanations

    Contains "in"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    och
    -0.27
    æĭī
    -0.25
    ltra
    -0.24
    ä¸Ĭæ¼Ķ
    -0.24
    (spec
    -0.24
    æĭīåįĩ
    -0.24
    æݨ
    -0.24
     reg
    -0.23
     Adjustment
    -0.23
    _exclude
    -0.23
    POSITIVE LOGITS
    ÃĤN
    0.26
     guiding
    0.25
    emachine
    0.24
    nell
    0.24
    å§ĭãĤģ
    0.24
    icles
    0.24
     Sellers
    0.23
    Mis
    0.23
    fila
    0.23
     fus
    0.23
    Activations Density 0.984%

    No Known Activations