© 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. 49526
    Prev
    Next
    INDEX
    Explanations

    your (ODF), mine (OOXML)

    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
     Iv
    -0.07
    æĬĹæĢ§
    -0.06
    iany
    -0.06
    igg
    -0.06
    åįļæł¼
    -0.06
    ç»ħ士
    -0.06
    ow
    -0.06
    [player
    -0.06
    ä½įåľ¨
    -0.06
    ++
    -0.06
    POSITIVE LOGITS
    è»
    0.08
    aka
    0.08
    端
    0.08
    ä¹Łå°±æĺ¯
    0.07
    æĸĩæijĺ
    0.07
    åıijé»Ħ
    0.07
    åħ¬å®īåİħ
    0.07
    erosis
    0.07
    inned
    0.07
    ãģ¥
    0.07
    Activations Density 0.045%

    No Known Activations