© 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. 35-TRANSCODER-HP
    7. 39929
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aget
    -0.28
     lap
    -0.26
     translate
    -0.26
     Radical
    -0.26
    å½·
    -0.25
     revolutions
    -0.25
    å¤ļ项
    -0.25
    æĸ°çļĦ
    -0.24
    rain
    -0.24
     radical
    -0.24
    POSITIVE LOGITS
    é¦ĸåħĪæĺ¯
    0.30
     therefore
    0.29
    arters
    0.27
    æĬĬ她
    0.27
    为主ä½ĵ
    0.26
    Basically
    0.26
    让ä»ĸ们
    0.26
    æīĵç®Ĺ
    0.25
     principally
    0.25
    åĴĮæĬĢæľ¯
    0.25
    Activations Density 1.051%

    No Known Activations