© 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. 8800
    Prev
    Next
    INDEX
    Explanations

    method for X

    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
    è±Ĩè±Ĩ
    -0.06
    abo
    -0.06
    ä¸įåĩĨ
    -0.06
    esson
    -0.06
     junk
    -0.06
    交æµģä¸İ
    -0.06
    oned
    -0.06
     Fa
    -0.06
    å°±æĺ¯åľ¨
    -0.06
    ä¸Ģæľµ
    -0.06
    POSITIVE LOGITS
    ervas
    0.08
    dle
    0.08
    edis
    0.08
    äºĪ
    0.08
    íĻĺ
    0.08
    (DIS
    0.07
    å¾·åįİ
    0.07
    Ĵ¤
    0.07
    olic
    0.07
    çļĦåŁºç¡Ģä¸Ĭ
    0.07
    Activations Density 0.557%

    No Known Activations