© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42230
    Prev
    Next
    INDEX
    Explanations

    pigment and melanin cells

    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
    baugh
    -0.08
    uffer
    -0.08
    alyzer
    -0.07
    liness
    -0.07
    entifier
    -0.07
    imate
    -0.07
     vá»įng
    -0.07
    ingly
    -0.06
    ertility
    -0.06
    åı£æ°Ķ
    -0.06
    POSITIVE LOGITS
    æ²īçĿĢ
    0.14
    aton
    0.09
    anton
    0.08
     melan
    0.08
    osity
    0.08
    çĹ£
    0.08
    ifer
    0.08
    less
    0.08
    Rgb
    0.08
    åĢ¾åŁİ
    0.08
    Activations Density 0.014%

    No Known Activations