© 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. 41425
    Prev
    Next
    INDEX
    Explanations

    OK KK

    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
    aram
    -0.08
    stre
    -0.07
    æķĻèĤ²åıijå±ķ
    -0.07
    æĪIJç«ł
    -0.07
    indy
    -0.07
     ÙħÙĤد
    -0.06
    ild
    -0.06
    æĪ®
    -0.06
    èĭ±æīį
    -0.06
    æīĢ欲
    -0.06
    POSITIVE LOGITS
    åIJĪä½ľäº¤æµģ
    0.09
     WHATSOEVER
    0.09
    artos
    0.08
    ommage
    0.08
     again
    0.07
    Again
    0.07
    çī¹çº¦
    0.07
    Ñħин
    0.07
     Teixe
    0.07
    again
    0.07
    Activations Density 0.006%

    No Known Activations