© 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. 19208
    Prev
    Next
    INDEX
    Explanations

    hash table rehash

    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
     inol
    -0.08
    æĹłåıį
    -0.07
    çļĦ计åĪĴ
    -0.07
    ROUTE
    -0.07
     заÑĢо
    -0.07
    leg
    -0.07
    请æĿ¥
    -0.07
    çħ§çĿĢ
    -0.07
    åħ¨éķĩ
    -0.07
    女æĢ§æľĭåıĭ
    -0.07
    POSITIVE LOGITS
    强åĪ¶
    0.09
     excess
    0.08
    æ¸ħç®Ĺ
    0.08
    被迫
    0.08
    aminer
    0.08
    èĩªåĬ¨
    0.08
    宿
    0.07
    assel
    0.07
    forced
    0.07
     избÑĭ
    0.07
    Activations Density 0.008%

    No Known Activations