© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    distraction osteogenesis

    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
    strup
    -0.08
    @param
    -0.07
    adius
    -0.07
    ADER
    -0.07
    çļĦåŃĺåľ¨
    -0.07
    åıĮèĬĤ
    -0.07
     luks
    -0.07
    @qq
    -0.07
     ÎŃγι
    -0.07
    मà¥Ģ
    -0.06
    POSITIVE LOGITS
    æĶ¿æ²»ä¸Ĭ
    0.10
    缸åºĶ
    0.09
     corresponding
    0.09
    对åºĶçļĦ
    0.09
    å±ĤéĿ¢
    0.08
     politico
    0.08
    缸æĩī
    0.08
    缸åºĶçļĦ
    0.08
    人äºĭ
    0.08
    çī©çIJĨ
    0.08
    Activations Density 0.446%

    No Known Activations