© 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. 40286
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ç®ĢåįķçļĦ
    -0.28
    zeros
    -0.26
     fel
    -0.26
    æ¯Ķè¾ĥç®Ģåįķ
    -0.25
     involuntary
    -0.25
    çŃĶå¤į
    -0.25
    èĬ±æł·
    -0.25
    çłĸ
    -0.25
    éª
    -0.24
    å°±çŁ¥éģĵ
    -0.24
    POSITIVE LOGITS
    oust
    0.29
    éĮ¢
    0.28
     precondition
    0.27
     PREF
    0.27
    大ä¼ļ
    0.26
    .parameter
    0.26
     visite
    0.26
    dana
    0.26
    liv
    0.26
    CAF
    0.25
    Activations Density 0.073%

    No Known Activations

    This feature has no known activations.