© 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. 51633
    Prev
    Next
    INDEX
    Explanations

    Copyright, Evil, alginate

    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
    æ³¢
    -0.06
    管çĶ¨
    -0.06
    æ¢
    -0.06
    å²ij
    -0.06
    èĩªåľ¨
    -0.06
     Nordest
    -0.05
    лем
    -0.05
    豪
    -0.05
     mand
    -0.05
    Core
    -0.05
    POSITIVE LOGITS
    è¶Ĭéķ¿
    0.08
    ensee
    0.07
    .eps
    0.07
    éĥ¨åĪĨåĨħ容
    0.07
    çľĭä¸Ģçľ¼
    0.07
    reja
    0.07
    èĩªå·±éĥ½
    0.07
     Sergey
    0.07
    esak
    0.07
    /umd
    0.07
    Activations Density 0.002%

    No Known Activations