© 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. 15756
    Prev
    Next
    INDEX
    Explanations

    metrics increasing or declining

    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
    Ļ
    -0.06
    éĻIJä»·
    -0.06
    询价
    -0.06
    kens
    -0.06
    erse
    -0.06
    èĥ¤
    -0.06
    渺
    -0.06
     manifest
    -0.06
    æ¡£ä½į
    -0.06
    循
    -0.06
    POSITIVE LOGITS
     total
    0.11
     totale
    0.10
    æĢ»éĩı
    0.10
    åįłåħ¨åĽ½
    0.10
    æĢ»éĩıçļĦ
    0.09
    æĢ»
    0.09
    åįłæĢ»
    0.09
    å¢ŀéĢŁ
    0.09
    åįłæ¯Ķ
    0.09
    ,total
    0.09
    Activations Density 0.442%

    No Known Activations