© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21799
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dani
    -0.07
    ML
    -0.07
    åħ¬åı¸æĭ¥æľī
    -0.07
     Skyl
    -0.06
    aston
    -0.06
    ml
    -0.06
    "F
    -0.06
    ÏĥÏĦÏĮ
    -0.06
    окÑģи
    -0.06
    ->
    -0.06
    POSITIVE LOGITS
    -Allow
    0.07
    isin
    0.07
    è·¯ç½ij
    0.07
    uffix
    0.07
    å½¢èī²
    0.06
    å°¤
    0.06
    :key
    0.06
    uitka
    0.06
    æł©æł©
    0.06
    -tool
    0.06
    Activations Density 0.068%

    No Known Activations