© 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. 14503
    Prev
    Next
    INDEX
    Explanations

    many different

    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
    ä¸į容
    -0.07
    kov
    -0.07
    驱
    -0.07
    è¿Ī
    -0.06
    igor
    -0.06
     Lim
    -0.06
    èݱ
    -0.06
    ª
    -0.06
    ObjectId
    -0.06
    utta
    -0.06
    POSITIVE LOGITS
    åıªè¦ģåľ¨
    0.11
    åıªè¦ģä½ł
    0.10
    åıªè¦ģ
    0.10
    满足äºİ
    0.09
     solange
    0.09
     varying
    0.09
     variations
    0.08
    vary
    0.08
     solutions
    0.08
    满足ä¸įåIJĮ
    0.08
    Activations Density 0.011%

    No Known Activations