© 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. 18672
    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
    amic
    -0.30
    ledo
    -0.29
    rends
    -0.27
    åıĸ
    -0.27
    .ASCII
    -0.26
    hiba
    -0.26
     multif
    -0.26
    udy
    -0.26
    ffee
    -0.25
    jem
    -0.25
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.31
    äºĨä¸Ģéģį
    0.30
     Frag
    0.28
    享åıĹ
    0.26
    å½
    0.26
    ;element
    0.26
    aders
    0.25
    æĻļ
    0.25
    宵
    0.25
    楯
    0.25
    Activations Density 0.130%

    No Known Activations

    This feature has no known activations.