© 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. 20-TRANSCODER-HP
    7. 131163
    Prev
    Next
    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    urs
    -0.29
     Amount
    -0.27
    éħį
    -0.26
    jective
    -0.25
    buzz
    -0.24
    çŃ¾
    -0.23
    æĸ°éĹ»è®°èĢħ
    -0.23
     murm
    -0.23
     Features
    -0.23
     advice
    -0.23
    POSITIVE LOGITS
    calar
    0.28
    åĽĽä¸ªæĦıè¯Ĩ
    0.26
    ansa
    0.26
    ä¾Ľæ±Ĥ
    0.26
    competitive
    0.26
    elige
    0.25
    _ASSUME
    0.24
    Invariant
    0.24
    overe
    0.24
     competitiveness
    0.24
    Activations Density 57.075%

    No Known Activations