© 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. 19290
    Prev
    Next
    INDEX
    Explanations

    Mixed Spanish and code/science

    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
    çīĩ
    -0.28
    nestjs
    -0.26
    sites
    -0.26
    __$
    -0.25
     interstate
    -0.25
    åĴ¬
    -0.25
     bitten
    -0.25
    [state
    -0.24
     -*-
    -0.24
     Greenwood
    -0.24
    POSITIVE LOGITS
     ancient
    0.27
    acente
    0.25
    ertools
    0.25
    unitÃł
    0.24
    aday
    0.24
    é¹Ħ
    0.24
    _BACK
    0.23
     trợ
    0.23
     eyeb
    0.23
    åĢºåĬ¡
    0.23
    Activations Density 6.243%

    No Known Activations