© 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. 17058
    Prev
    Next
    INDEX
    Explanations

    endocrine neuroendocrine

    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
    æıīäºĨ
    -0.08
    ç³Ļ
    -0.07
    彬
    -0.07
    kah
    -0.07
    微信æī«çłģ
    -0.07
    orza
    -0.06
    åºķ线
    -0.06
     mire
    -0.06
    iped
    -0.06
    并ä¸į大
    -0.06
    POSITIVE LOGITS
    voc
    0.08
    éķ¿ç©º
    0.08
    åī§æ¯Ĵ
    0.08
    gas
    0.08
    omba
    0.08
     perfume
    0.07
    ä¸Ńæ¯Ĵ
    0.07
    irsch
    0.07
     Fischer
    0.07
    еÑĤка
    0.07
    Activations Density 0.016%

    No Known Activations