© 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. 24958
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
     konk
    -0.29
    asm
    -0.27
    prung
    -0.27
    ombs
    -0.25
     ÑģооÑĤвеÑĤ
    -0.25
    ôme
    -0.24
    év
    -0.24
    ankan
    -0.24
    ä¸Ī
    -0.24
    elves
    -0.24
    POSITIVE LOGITS
    éķ¿çŁŃ
    0.28
     trillion
    0.24
     Fre
    0.24
    aptive
    0.23
    iant
    0.23
    å¾ħ
    0.23
    -short
    0.23
     MS
    0.23
     Sachs
    0.23
     lif
    0.22
    Activations Density 0.080%

    No Known Activations