© 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. 12-TRANSCODER-HP
    7. 23845
    Prev
    Next
    INDEX
    Explanations

    4

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĥŁ
    -0.28
    (Level
    -0.28
    ilden
    -0.27
    ickers
    -0.25
    (ln
    -0.24
    (([
    -0.24
    -book
    -0.24
    è¡Į为
    -0.23
    inea
    -0.23
    ä¿ij
    -0.23
    POSITIVE LOGITS
    å¥īçĮ®
    0.29
    itics
    0.27
    æĩ
    0.27
    è´¡çĮ®
    0.27
    åĨ¤
    0.27
    .mo
    0.26
    æĤ¬
    0.26
    peng
    0.26
    jian
    0.26
     contribution
    0.25
    Activations Density 0.010%

    No Known Activations