© 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. 56595
    Prev
    Next
    INDEX
    Explanations

    theoretical basis for future work

    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
     Hands
    -0.08
    ska
    -0.08
    áĢ±áĢ¸
    -0.07
    ovina
    -0.07
    locked
    -0.07
    Singleton
    -0.07
    ä¸įç®Ģåįķ
    -0.07
    ponsored
    -0.07
     incont
    -0.07
    _repr
    -0.07
    POSITIVE LOGITS
    åŁºç¡Ģ
    0.12
     foundation
    0.12
     basis
    0.11
     groundwork
    0.11
     Grundlage
    0.10
    åĿļå®ŀåŁºç¡Ģ
    0.10
    åĿļå®ŀçļĦåŁºç¡Ģ
    0.10
    basis
    0.10
    åŁºç¡ĢåĴĮ
    0.10
    æĶ¯æĮģ
    0.10
    Activations Density 0.070%

    No Known Activations