© 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. 39722
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .Initialize
    -0.28
    çĻ¾ä¸ĩ
    -0.25
    ouch
    -0.25
    .attach
    -0.24
     Initializes
    -0.24
    amentos
    -0.24
     initializes
    -0.24
    æĺ¯æĮĩ
    -0.23
    Initialize
    -0.23
    éĺ³
    -0.23
    POSITIVE LOGITS
    limits
    0.27
    æĬł
    0.25
    leta
    0.25
    é«ĺå³°
    0.24
    åľ¨äº¬
    0.24
     Midi
    0.24
    平稳
    0.24
    udad
    0.24
    ä¸įåģľçļĦ
    0.24
    é«ĺå³°æľŁ
    0.23
    Activations Density 2.043%

    No Known Activations