© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40862
    Prev
    Next
    INDEX
    Explanations

    instructions and explanations

    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
    sg
    -0.24
    ĺ认
    -0.24
     prof
    -0.23
    å¿«
    -0.23
     contradict
    -0.23
     appreciate
    -0.23
    æķĻæİĪ
    -0.23
    éĻ¢
    -0.23
     lost
    -0.23
    series
    -0.23
    POSITIVE LOGITS
    bows
    0.30
    -guard
    0.27
    .Dispatcher
    0.26
    ç¾Ł
    0.26
    NECT
    0.25
    åīį身
    0.25
    ELY
    0.25
    KY
    0.24
    å½¢æĪIJ
    0.24
    åºľ
    0.24
    Activations Density 0.435%

    No Known Activations