© 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. 31-TRANSCODER-HP
    7. 18915
    Prev
    Next
    INDEX
    Explanations

    technical and scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ira
    -0.31
    æijĺç¼ĸ
    -0.29
    IRA
    -0.29
     comm
    -0.28
    åĪĨ离
    -0.28
    uzzi
    -0.27
    iations
    -0.27
     Comm
    -0.27
    elmet
    -0.27
    omm
    -0.26
    POSITIVE LOGITS
    Lookup
    0.27
    catalog
    0.27
    itches
    0.27
    GEST
    0.26
    stin
    0.25
     infl
    0.25
     Catalog
    0.25
    çªĹæĪ·
    0.25
    kie
    0.25
    _catalog
    0.25
    Activations Density 0.001%

    No Known Activations