© 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. 18-TRANSCODER-HP
    7. 88652
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Portions
    -0.28
     Alam
    -0.28
     Aeros
    -0.26
    yntax
    -0.25
     Nos
    -0.25
    æĿĥ
    -0.24
    éĢł
    -0.23
    اعت
    -0.23
    åĭģ
    -0.23
    Sys
    -0.23
    POSITIVE LOGITS
    gaard
    0.27
    halt
    0.26
    stein
    0.24
    '^$',
    0.24
     automat
    0.23
     mand
    0.23
    »
    0.23
    лав
    0.23
     halt
    0.22
    _KIND
    0.22
    Activations Density 4.346%

    No Known Activations

    This feature has no known activations.