© 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. 41623
    Prev
    Next
    INDEX
    Explanations

    writers, tutors, experts, performers

    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
    åĮ£
    -0.08
    æĬ¹
    -0.08
    igger
    -0.07
    lbrace
    -0.07
    çĪ±æĪij
    -0.07
    _pref
    -0.07
    主è¦ģçļĦ
    -0.07
     Bulletin
    -0.07
    éĽªèĬ±
    -0.07
    æŃī
    -0.07
    POSITIVE LOGITS
     Tutor
    0.08
     tutors
    0.08
    ä¸ĵå®¶åĽ¢éĺŁ
    0.08
     instant
    0.08
    instant
    0.08
    æ¨ĭ
    0.08
     tutoring
    0.07
    IfExists
    0.07
     expert
    0.07
    -chat
    0.07
    Activations Density 0.285%

    No Known Activations