© 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. 3646
    Prev
    Next
    INDEX
    Explanations

    organic disorders

    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
    ifact
    -0.08
    òi
    -0.08
    ẩm
    -0.08
    пÑĢом
    -0.07
    ¶ļ
    -0.07
    ếm
    -0.07
    еÑģпе
    -0.07
    ừa
    -0.07
    ummies
    -0.07
    umpang
    -0.07
    POSITIVE LOGITS
    ä¸Ńèĭ±
    0.06
    fullscreen
    0.06
     Dra
    0.06
    entin
    0.06
    çĥŃ身
    0.06
    باØŃ
    0.06
     cardi
    0.06
    ok
    0.06
    æİĴ忧
    0.06
    webs
    0.06
    Activations Density 0.914%

    No Known Activations