© 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. 30443
    Prev
    Next
    INDEX
    Explanations

    data for regression or analysis

    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
    ozy
    -0.07
    ibox
    -0.07
    è¿ħéĢŁ
    -0.06
    _hits
    -0.06
    èĥĨ
    -0.06
     Alc
    -0.06
    åºĶæĢ¥åĵįåºĶ
    -0.06
    å²ģéĤ£å¹´
    -0.06
    ouser
    -0.06
    łí
    -0.06
    POSITIVE LOGITS
     data
    0.11
    æķ°æį®ç±»åŀĭ
    0.11
    æķ°æį®çļĦ
    0.10
    æķ°æį®
    0.10
    Ordinal
    0.09
     datasets
    0.09
     Data
    0.09
    è¿ĻäºĽæķ°æį®
    0.09
    data
    0.09
    æķ°æį®è¿Ľè¡Į
    0.09
    Activations Density 0.073%

    No Known Activations