© 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. 19610
    Prev
    Next
    INDEX
    Explanations

    in-situ, on-site

    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
    èĩªçĶ±
    -0.08
    caster
    -0.07
     misi
    -0.07
    è®¤çľŁåľ°
    -0.06
     indul
    -0.06
    çĭ¬è¡Į
    -0.06
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.06
    lug
    -0.06
    bull
    -0.06
    ofire
    -0.06
    POSITIVE LOGITS
    å°±åľ°
    0.13
    缴æİ¥åľ¨
    0.11
     langsung
    0.11
     directly
    0.10
    缴æİ¥
    0.09
     Langsung
    0.09
    å½ĵåľº
    0.09
    åį³åľ¨
    0.09
     embedded
    0.09
    ä¹Łåı¯çĽ´æİ¥
    0.09
    Activations Density 0.325%

    No Known Activations