© 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. 9690
    Prev
    Next
    INDEX
    Explanations

    in column value click

    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
    onger
    -0.08
    请åĴ¨è¯¢
    -0.06
    orse
    -0.06
     Weih
    -0.06
    اة
    -0.06
    åĬŁçĶ¨
    -0.06
    æ·¡éĽħ
    -0.06
     captures
    -0.06
    ä¿ĺèĻı
    -0.06
    åħ¨éĥ¨éĥ½æĺ¯
    -0.06
    POSITIVE LOGITS
    ahl
    0.09
    nox
    0.08
    olver
    0.08
    erste
    0.08
    italic
    0.07
     Centrale
    0.07
    åĪĩåħ¥çĤ¹
    0.07
    ipment
    0.07
    åľ¨ç¬¬
    0.07
    _ANY
    0.07
    Activations Density 0.002%

    No Known Activations