© 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. 28632
    Prev
    Next
    INDEX
    Explanations

    Subject/doc comments

    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
    izable
    -0.07
    ilus
    -0.07
    éĻĪå°ı
    -0.07
    arca
    -0.07
    rip
    -0.07
    ãģ£ãģ¦ãģ¿ãģŁ
    -0.06
    _ORIGIN
    -0.06
    æ¼Ĥ
    -0.06
     καθη
    -0.06
     Fen
    -0.06
    POSITIVE LOGITS
    bior
    0.08
    onton
    0.08
    acas
    0.07
    efon
    0.07
    好åķĬ
    0.07
    otá
    0.07
    ikota
    0.07
    ickers
    0.07
    cken
    0.06
    иÑĤо
    0.06
    Activations Density 0.010%

    No Known Activations