© 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. 25-TRANSCODER-HP
    7. 108668
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩłå®¶
    -0.31
    åijĹ
    -0.29
    è¾Ł
    -0.28
     propos
    -0.27
     proposals
    -0.26
    holder
    -0.25
    æĻķ
    -0.25
     proposal
    -0.25
    åįĥåı¤
    -0.24
    Bring
    -0.24
    POSITIVE LOGITS
    æĴŃ
    0.29
    æ¾į
    0.27
    cher
    0.27
    /GPL
    0.26
     Issue
    0.25
     Sonic
    0.25
    æĸ°è¥¿
    0.24
    _RT
    0.23
    proj
    0.23
     ET
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.