© 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. 23394
    Prev
    Next
    INDEX
    Explanations

    sqrt(605), conventional, Deliveroo

    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
    大åij¼
    -0.08
    æĸĽ
    -0.08
    ToStr
    -0.07
    olet
    -0.07
    ana
    -0.07
    Want
    -0.07
    ä¿IJ
    -0.07
    ç¿©
    -0.07
    eday
    -0.07
    åıªåĽł
    -0.07
    POSITIVE LOGITS
    æĢ»ä¹ĭ
    0.08
    æīĢ以说
    0.07
    ourn
    0.07
    æĻ¯æ°Ķ
    0.07
    gen
    0.06
     gen
    0.06
    osaic
    0.06
    æĢ»èĢĮè¨Ģä¹ĭ
    0.06
    åı¯ä»¥çĤ¹åĩ»
    0.06
     anyways
    0.06
    Activations Density 0.006%

    No Known Activations