© 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. 49613
    Prev
    Next
    INDEX
    Explanations

    license types or abbreviations

    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
    ç¾İæľ¯åѦéĻ¢
    -0.10
     manner
    -0.09
    mate
    -0.09
     majeure
    -0.09
    çĮĽåħ½
    -0.08
     ë§Ī볨
    -0.08
     maje
    -0.08
     mặt
    -0.08
    magnitude
    -0.08
     mẫu
    -0.08
    POSITIVE LOGITS
    intosh
    0.13
    ellaneous
    0.13
     mẽ
    0.13
    ifest
    0.12
     Madness
    0.12
    Carthy
    0.12
     Mondays
    0.11
    ificent
    0.11
    iscal
    0.11
    roring
    0.10
    Activations Density 2.894%

    No Known Activations