© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18111
    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
    mı
    -0.30
    ·»
    -0.30
     Brend
    -0.29
     conduct
    -0.29
     Conduct
    -0.29
    /lists
    -0.28
    ä¾ĭè¡Į
    -0.26
    _EXISTS
    -0.25
     conductor
    -0.25
    inq
    -0.25
    POSITIVE LOGITS
    animal
    0.36
     animal
    0.35
    åĬ¨çī©
    0.34
     Animal
    0.33
    itched
    0.30
    Animal
    0.29
     crust
    0.28
    åħ½
    0.28
    çį¸
    0.28
    itch
    0.27
    Activations Density 0.087%

    No Known Activations