© 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. 10552
    Prev
    Next
    INDEX
    Explanations

    R or IR to plane

    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
    æ±Ĥç²¾
    -0.08
    çľģå§Ķ
    -0.08
    orman
    -0.08
    emi
    -0.08
    被åĪ«äºº
    -0.08
    æĪĸ缴æİ¥
    -0.07
    éĩĮéĿ¢æľī
    -0.07
    æĭīèĤļåŃIJ
    -0.07
    åľ¨çľģ
    -0.07
    çľģæķĻèĤ²åİħ
    -0.07
    POSITIVE LOGITS
    åħ¨å¤©åĢĻ
    0.07
    utan
    0.07
    å¹³åĿ¦
    0.07
    åħ¨å¹´
    0.07
    -span
    0.07
     entirety
    0.07
    JsonValue
    0.06
     fol
    0.06
    åħ¨å¤©
    0.06
    udy
    0.06
    Activations Density 0.013%

    No Known Activations