© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 892
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    ensee
    -0.08
    apos
    -0.07
    _ARGS
    -0.07
    _funcs
    -0.07
    irate
    -0.07
    çĿĢæĪij们çļĦ
    -0.07
     elog
    -0.07
    oslav
    -0.07
    ãģ§ãģĻãĤĪ
    -0.07
    еÑģÑĤв
    -0.07
    POSITIVE LOGITS
    ä¸ĢéĹ®
    0.08
    éĹ®éģĵ
    0.08
     deeper
    0.08
    åį´ä¸įçŁ¥éģĵ
    0.08
     further
    0.08
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    0.07
    æĽ´æ·±
    0.07
    è¿Ľä¸ĢæŃ¥çļĦ
    0.07
     deepen
    0.07
    çļĦéĹ®éģĵ
    0.07
    Activations Density 0.098%

    No Known Activations