© 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. 51542
    Prev
    Next
    INDEX
    Explanations

    services and business offerings

    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
     Pinto
    -0.07
    æĪijåĢĴ
    -0.06
    QR
    -0.06
    aki
    -0.06
    eki
    -0.06
    髦
    -0.06
    æĶ¯
    -0.05
    _STYLE
    -0.05
    以å¾ħ
    -0.05
    åĨ³ä¸į
    -0.05
    POSITIVE LOGITS
    å°½åľ¨
    0.09
    diy
    0.08
    atriz
    0.08
     âĸ·
    0.08
    itemap
    0.08
    éĿ¢çĽ¸
    0.08
    veil
    0.07
    |#
    0.07
    áĢ»
    0.07
    assing
    0.07
    Activations Density 1.262%

    No Known Activations