© 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. 40531
    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
    ADOW
    -0.27
    omore
    -0.26
    oten
    -0.26
    è¿Ļ两ç§į
    -0.25
    Fmt
    -0.24
    å¹´æĬ¥
    -0.24
    .realm
    -0.24
    @c
    -0.24
    尺度
    -0.24
     dua
    -0.23
    POSITIVE LOGITS
    elves
    0.30
     shedding
    0.27
    线ä¸Ĭ线ä¸ĭ
    0.25
    shed
    0.25
     alternate
    0.25
     shed
    0.24
    ç´¯
    0.24
    ık
    0.23
     slic
    0.23
    certificate
    0.23
    Activations Density 0.321%

    No Known Activations

    This feature has no known activations.