© 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. 34677
    Prev
    Next
    INDEX
    Explanations

    osteoradionecrosis, first, versus

    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
    boll
    -0.08
    æĪIJè¿Ļæł·
    -0.08
    Dirs
    -0.08
    è¿Ł
    -0.08
    è¡ĮæĿİç®±
    -0.07
    è¿Ļä¹Īç®Ģåįķ
    -0.07
    çĴ¨
    -0.07
    çŁ¥ä¹ĭ
    -0.07
    BOOLE
    -0.07
    URRE
    -0.07
    POSITIVE LOGITS
    erei
    0.07
    akah
    0.06
    _vs
    0.06
    便æĺ¯
    0.06
    åĢ¦
    0.06
    æ±ĩ
    0.06
    irst
    0.06
     λοι
    0.06
     versus
    0.06
     broader
    0.06
    Activations Density 0.025%

    No Known Activations