© 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. 60432
    Prev
    Next
    INDEX
    Explanations

    file path components and code snippets

    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
    tere
    -0.07
    çªĿ
    -0.07
    erot
    -0.06
    ter
    -0.06
    woord
    -0.06
    eo
    -0.06
     (£
    -0.06
    krat
    -0.06
    ä¹ĭæģ©
    -0.06
    _EP
    -0.06
    POSITIVE LOGITS
    isson
    0.08
    æľīä½Ļ
    0.08
    ë²Īíĺ¸
    0.07
     Holder
    0.07
    æѤäºĭ
    0.07
    .gnu
    0.07
    çĩ
    0.07
    olas
    0.07
    pera
    0.07
    cion
    0.07
    Activations Density 0.415%

    No Known Activations