© 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. 18995
    Prev
    Next
    INDEX
    Explanations

    concept development or prototypes

    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
    lander
    -0.07
     operated
    -0.06
     arre
    -0.06
    é¡»çŁ¥
    -0.06
     configured
    -0.06
     disable
    -0.06
    zeg
    -0.06
    人ä¸į
    -0.06
     specially
    -0.06
    å¤į产
    -0.06
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.13
    èįī
    0.12
    æݨæķ²
    0.12
    èįī稿
    0.11
    æŀĦæĢĿ
    0.11
     rough
    0.11
    éĽıå½¢
    0.10
     sketches
    0.10
     prelim
    0.10
    รà¹Īาà¸ĩ
    0.10
    Activations Density 0.165%

    No Known Activations