© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23911
    Prev
    Next
    INDEX
    Explanations

    spaces or special characters

    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
    egan
    -0.08
    ä¿Ŀå®Ī
    -0.08
     سرا
    -0.07
     blind
    -0.07
    onte
    -0.07
    .setBackgroundColor
    -0.07
    ä»İæĹł
    -0.07
    AKAN
    -0.07
     banh
    -0.06
    ahlen
    -0.06
    POSITIVE LOGITS
    æ··
    0.08
    æ··æĿĤ
    0.08
    æł¼å¼ı
    0.08
    夹æĿĤ
    0.07
     stray
    0.07
    æł¼å¼ıçļĦ
    0.07
    å¤ļä½ĻçļĦ
    0.07
    æĪĸåħ¶ä»ĸ
    0.07
    çŃīæĥħåĨµ
    0.07
    临éŨ
    0.07
    Activations Density 0.046%

    No Known Activations