© 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. 29113
    Prev
    Next
    INDEX
    Explanations

    file format structure

    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
    satz
    -0.08
    ActivityResult
    -0.08
    AdapterManager
    -0.08
    è¾ľ
    -0.08
    -assets
    -0.08
    ä¹ĭæľ¬
    -0.08
    SetBranch
    -0.08
    olk
    -0.08
    asses
    -0.08
    JKLM
    -0.08
    POSITIVE LOGITS
     interle
    0.09
     format
    0.09
    æł¼å¼ı
    0.09
    æł¼å¼ıçļĦ
    0.08
     concatenated
    0.08
    andatory
    0.07
    ç´§æİ¥çĿĢ
    0.07
     concaten
    0.07
     formatted
    0.07
     single
    0.07
    Activations Density 0.040%

    No Known Activations