© 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. 29370
    Prev
    Next
    INDEX
    Explanations

    numbers in computations or identifiers

    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
    æĹłæļĩ
    -0.07
    _REPLACE
    -0.07
    à¯įதà¯įத
    -0.07
    BUFFER
    -0.07
    çĥŃæIJľè¯į
    -0.07
    à¯įத
    -0.07
    اتÛĮ
    -0.07
    çļĦäººä¹Ł
    -0.06
    vos
    -0.06
    abl
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    elda
    0.07
    éĻĨ
    0.07
    erti
    0.07
    æĬĺ
    0.07
    iec
    0.07
    åħ¶æīĢ
    0.07
    äºļäºİ
    0.06
    ç«ĭãģ¦
    0.06
    ãģ©ãģĵãĤį
    0.06
    Activations Density 0.064%

    No Known Activations