© 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. 60571
    Prev
    Next
    INDEX
    Explanations

    abstract or introduction sections

    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
    ity
    -0.08
    veen
    -0.06
    ya
    -0.06
    wear
    -0.06
    æīĢ
    -0.06
    пли
    -0.06
    è½½
    -0.06
    Âł
    -0.06
    anker
    -0.05
    温æŁĶ
    -0.05
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.09
    ä¸ĢæıIJ
    0.09
    _cpus
    0.08
    èݱåĿŀ
    0.08
    ikka
    0.08
    å±ī
    0.08
    Cls
    0.08
    egah
    0.08
    ç«¯æľ¨
    0.08
    çijŁ
    0.08
    Activations Density 0.017%

    No Known Activations