© 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. 25-TRANSCODER-HP
    7. 107432
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _languages
    -0.30
     Lump
    -0.26
    elson
    -0.25
    .nr
    -0.25
    ä¸Ģ侧
    -0.25
    languages
    -0.25
     osob
    -0.25
    å©¿
    -0.24
    çļĦ人çī©
    -0.24
    åıĺå¾Ĺ
    -0.24
    POSITIVE LOGITS
    ÄĴ
    0.28
    ogene
    0.26
    rena
    0.25
    .'<
    0.25
    ICY
    0.24
    æĸł
    0.24
     Town
    0.24
     curs
    0.23
    dere
    0.23
     town
    0.23
    Activations Density 0.909%

    No Known Activations