© 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. 23-TRANSCODER-HP
    7. 25304
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lâ
    -0.31
    #undef
    -0.27
    nest
    -0.25
    æĸ¯åŁº
    -0.24
    TTY
    -0.24
    :eq
    -0.24
    æĭ¿èµ·
    -0.23
    åħ³éĶ®æĺ¯
    -0.23
    ardy
    -0.23
    tright
    -0.23
    POSITIVE LOGITS
    éĢĢ
    0.26
    ployment
    0.25
    боÑĢ
    0.24
    åĬŁåĬ³
    0.24
    .dk
    0.24
    ailles
    0.24
    ĻĤ
    0.23
    apore
    0.23
    ä¸Ģè§Ĵ
    0.23
    ersist
    0.23
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.