© 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. 18841
    Prev
    Next
    INDEX
    Explanations

    .com suffix

    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
    æĥħæĦ¿
    -0.07
    ,
    -0.06
     human
    -0.06
    æ¦Ĥ论
    -0.06
     $($
    -0.06
    acers
    -0.06
     kÃŃ
    -0.06
     Human
    -0.06
    ?s
    -0.05
    èĦļæŃ¥
    -0.05
    POSITIVE LOGITS
    </think>
    0.09
    _Pos
    0.08
    isclosed
    0.08
    chow
    0.08
     reda
    0.08
    udara
    0.08
    urar
    0.08
    är
    0.08
    eles
    0.07
    天ä»Ļ
    0.07
    Activations Density 0.004%

    No Known Activations