© 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. 32-TRANSCODER-HP
    7. 43403
    Prev
    Next
    INDEX
    Explanations

    technical/code-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     synthetic
    -0.28
    nice
    -0.28
     outs
    -0.27
    cle
    -0.26
    åIJİæİĴ
    -0.26
    orde
    -0.25
    éŁŃèıľ
    -0.25
     Ãĸz
    -0.24
     syn
    -0.24
    ONT
    -0.24
    POSITIVE LOGITS
    æĴĴ
    0.25
     Wyatt
    0.24
    shine
    0.24
    ç¥ĩ
    0.23
     Speedway
    0.23
    #![
    0.23
    .fx
    0.23
    (buff
    0.23
    ewriter
    0.23
     Haut
    0.23
    Activations Density 0.000%

    No Known Activations