© 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. 63250
    Prev
    Next
    INDEX
    Explanations

    erythrocyte or red blood cell

    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
    issa
    -0.08
    æŃ¥æŃ¥
    -0.08
    å¤ļéĥ¨
    -0.07
    æŀĿåı¶
    -0.07
    èĭĵ
    -0.07
    ingerie
    -0.07
     rá»ħ
    -0.07
    endem
    -0.07
    oru
    -0.07
    θεν
    -0.07
    POSITIVE LOGITS
    红ç»Ĩèĥŀ
    0.10
    çļĦè¡Ģ
    0.10
    è¡Ģ
    0.09
    è¡Ģ红èĽĭçĻ½
    0.09
     blood
    0.09
     circulating
    0.09
     кÑĢови
    0.08
     circulation
    0.08
    æīģå¹³
    0.08
    è¡ĢçļĦ
    0.08
    Activations Density 0.053%

    No Known Activations