© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    radical prostate

    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
    onger
    -0.07
    obuf
    -0.07
     Smarty
    -0.07
    obili
    -0.06
    ÎŃν
    -0.06
    gency
    -0.06
    umus
    -0.06
    ertura
    -0.06
     AABB
    -0.06
    è¿ĻæĬĬ
    -0.06
    POSITIVE LOGITS
     via
    0.15
     online
    0.14
    Via
    0.13
    线ä¸Ĭ线ä¸ĭ
    0.12
    via
    0.12
     offline
    0.12
    åľ¨çº¿
    0.12
     vÃŃa
    0.12
    online
    0.12
     either
    0.12
    Activations Density 2.229%

    No Known Activations