© 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. 49759
    Prev
    Next
    INDEX
    Explanations

    death, prime ministers, species, station, per, county

    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
    enth
    -0.07
    æĢ§æĪĸ
    -0.07
    ...)
    -0.07
    ä¼
    -0.06
     ...)
    -0.06
    çº
    -0.06
    è¤ĩ
    -0.06
    çŃīæĸ¹å¼ı
    -0.06
    kid
    -0.06
    復
    -0.06
    POSITIVE LOGITS
     tehát
    0.08
    usak
    0.07
    å°±æĺ¯è¿Ļä¹Ī
    0.07
    ÎijΣ
    0.06
    éĢļè¿ĩ以ä¸Ĭ
    0.06
    ichern
    0.06
    รà¸Ńà¸Ķ
    0.06
    ÐŃÐļ
    0.06
    ISTRA
    0.06
    æĮģç»Ńåıijå±ķ
    0.06
    Activations Density 0.023%

    No Known Activations