© 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. 23368
    Prev
    Next
    INDEX
    Explanations

    Code/technical documents

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    @hotmail
    -0.30
    icer
    -0.28
    rops
    -0.26
    otron
    -0.26
     awhile
    -0.26
    .opend
    -0.26
    ide
    -0.25
    .Scheme
    -0.25
    IPH
    -0.25
    ofilm
    -0.25
    POSITIVE LOGITS
    utto
    0.29
    ä½įç½®
    0.27
    Foot
    0.25
    èĬŃ
    0.25
    noch
    0.24
    åĹľ
    0.24
    (cont
    0.24
    éĢŁåº¦
    0.24
    .weights
    0.24
     Original
    0.23
    Activations Density 0.007%

    No Known Activations