© 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. 29405
    Prev
    Next
    INDEX
    Explanations

    NONPRECEDENTIAL DISPOSITION

    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
    Ùĩ
    -0.10
    ìį¨
    -0.08
    æł·çļĦ
    -0.08
    ized
    -0.08
    -0.07
    ously
    -0.07
    失æݪ
    -0.07
    è§ģå¾Ĺ
    -0.07
    kort
    -0.07
    ieso
    -0.07
    POSITIVE LOGITS
    enticate
    0.12
    Ø©
    0.11
    sWith
    0.11
    s
    0.10
    ãģĦãĤĭ
    0.10
    ëĤĺê°Ģ
    0.10
    ti
    0.10
    ness
    0.09
    缸è¾ħ缸æĪIJ
    0.09
     Âł Âł Âł Âł
    0.09
    Activations Density 0.037%

    No Known Activations