© 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. 23-TRANSCODER-HP
    7. 23849
    Prev
    Next
    INDEX
    Explanations

    Code operators and file encoding

    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
    Not in Any Lists

    No Comments

    Negative Logits
    postData
    -0.28
    $insert
    -0.25
    ilty
    -0.25
    åĩºéŨ
    -0.24
    лей
    -0.23
    аÑĢÑĮ
    -0.23
     Syn
    -0.23
    /dr
    -0.23
    antry
    -0.23
    .desktop
    -0.23
    POSITIVE LOGITS
    cpy
    0.30
     Jacqu
    0.26
    ensi
    0.25
     unf
    0.25
    å°ķ
    0.24
    vic
    0.24
     IonicPage
    0.23
    Toolkit
    0.23
    Reviewed
    0.23
    pot
    0.23
    Activations Density 0.011%

    No Known Activations