© 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. 107430
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    ä¸įè´Ł
    -0.29
    ioned
    -0.27
     اÙĦعرب
    -0.26
    orra
    -0.25
    geh
    -0.25
    æĺ¯å¦Ĥä½ķ
    -0.24
    [/
    -0.24
    urgent
    -0.24
    éĢļè¡Įè¯ģ
    -0.24
    flat
    -0.24
    POSITIVE LOGITS
    山谷
    0.27
    ohan
    0.26
    anken
    0.24
    åĽ°æĥij
    0.24
    è¾Ł
    0.24
    éric
    0.24
    å·²ç»ıæľī
    0.24
    åħ¼
    0.24
    è¡
    0.24
    nP
    0.23
    Activations Density 0.948%

    No Known Activations