© 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. 27-TRANSCODER-HP
    7. 9260
    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_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [].
    -0.28
    è¾ĥé«ĺçļĦ
    -0.27
    ä¸Ģéĥ¨
    -0.26
    æĺ¯å¾Ī
    -0.26
    æĺ¯æ¯Ķè¾ĥ
    -0.25
    çļĦåĸľçĪ±
    -0.25
    ').
    -0.25
    è½´
    -0.25
    '.
    -0.24
    '].
    -0.24
    POSITIVE LOGITS
     reside
    0.30
     occupy
    0.29
    æºī
    0.29
     originate
    0.28
    tü
    0.28
     nest
    0.27
    åı«
    0.27
    åIJģ
    0.26
    æĿ¥èĩª
    0.26
    aque
    0.26
    Activations Density 0.014%

    No Known Activations