© 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. 24551
    Prev
    Next
    INDEX
    Explanations

    epithelial cells or companion objects

    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
    åıijå±ķä¸İ
    -0.08
    åģļçļĦå°±æĺ¯
    -0.07
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    -0.07
    ç»ĵæŀĦä¸İ
    -0.07
    .PNG
    -0.06
     Foley
    -0.06
     ÙħختÙĦÙģÛĮ
    -0.06
    å¼Ģåıijä¸İ
    -0.06
    uzzi
    -0.06
     RegExp
    -0.06
    POSITIVE LOGITS
    included
    0.07
     aanwez
    0.07
    ört
    0.07
     whilst
    0.07
     ÙĪبÙĬÙĨ
    0.07
    during
    0.06
    intÄĥ
    0.06
    èħ±
    0.06
    amenta
    0.06
     contained
    0.06
    Activations Density 0.688%

    No Known Activations