© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22955
    Prev
    Next
    INDEX
    Explanations

    not simply or easily

    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
    uschen
    -0.08
    åħ·å¤ĩä¸Ģå®ļçļĦ
    -0.08
     never
    -0.08
    elman
    -0.08
    acist
    -0.08
    boll
    -0.08
    ä¸įåĪ°çļĦ
    -0.07
    elcome
    -0.07
    æĽ¾è¡¨ç¤º
    -0.07
    never
    -0.07
    POSITIVE LOGITS
     easily
    0.11
     directly
    0.11
    缴æİ¥
    0.10
    ä¸Ģä¸ĭåŃIJ
    0.10
    缴æİ¥çĶ¨
    0.09
     readily
    0.08
    缴æİ¥çļĦ
    0.08
     nicely
    0.08
    è½»æĺĵ
    0.08
     напÑĢÑıмÑĥÑİ
    0.08
    Activations Density 0.193%

    No Known Activations