© 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. 31-TRANSCODER-HP
    7. 19138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opian
    -0.29
     sleeper
    -0.28
    umat
    -0.27
    æ©Ħæ¦Ħ
    -0.27
    çħ
    -0.27
    tings
    -0.26
    duplicate
    -0.25
     cf
    -0.25
    cel
    -0.24
    CEE
    -0.24
    POSITIVE LOGITS
    ä¹ĭéĹ´çļĦ
    0.27
    åįıä¼ļ
    0.26
    rios
    0.25
    åįıä¼ļä¼ļéķ¿
    0.25
    ños
    0.25
    ä¸įä¸Ĭ
    0.25
    .Logic
    0.24
    ä¹ĭä¸Ń
    0.24
    maj
    0.24
    æĿĢ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.