© 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. 43897
    Prev
    Next
    INDEX
    Explanations

    bacterial

    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
    ä½ĻåĬĽ
    -0.08
    ýt
    -0.07
    endt
    -0.07
    åĬ³éĢ¸
    -0.07
    è¿Ł
    -0.07
    ÛĮÙĤ
    -0.07
    æĶ¯åĩºçļĦ
    -0.07
    impa
    -0.07
    à¸Ńรà¹Į
    -0.07
    antie
    -0.07
    POSITIVE LOGITS
     bacter
    0.08
    ç»ĵæŀĦç®Ģåįķ
    0.08
     simplicity
    0.08
     simpler
    0.08
     bacteria
    0.08
    ç®ĢåįķçļĦ
    0.08
     bacterial
    0.08
     пÑĢока
    0.08
    ç»ĨèıĮ
    0.08
    å¾®çĶŁçī©
    0.07
    Activations Density 0.026%

    No Known Activations