© 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. 38446
    Prev
    Next
    INDEX
    Explanations

    contact Us / inquiries

    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
    åħ¬åı¸èį£èªī
    -0.07
    æĸĩæijĺ
    -0.07
    uhi
    -0.07
    ç§ijæĬĢåѦéĻ¢
    -0.07
    ео
    -0.07
    setError
    -0.07
     seguid
    -0.06
    GOR
    -0.06
    åľ¨çº¿éĺħ读
    -0.06
    _TRY
    -0.06
    POSITIVE LOGITS
    èģĶç³»
    0.11
     inquiries
    0.10
    èģĶç³»çļĦ
    0.10
    åıĸå¾ĹèģĶç³»
    0.10
     enquiries
    0.10
     contact
    0.10
    _contact
    0.09
     contacts
    0.09
    /contact
    0.09
    (Contact
    0.09
    Activations Density 0.191%

    No Known Activations