© 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. 45059
    Prev
    Next
    INDEX
    Explanations

    biggest value

    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
    æĹ¶è®¸
    -0.09
    erber
    -0.09
    angnya
    -0.08
    aub
    -0.08
    ildo
    -0.08
     Jorn
    -0.08
    _ATT
    -0.07
    irin
    -0.07
    idth
    -0.07
    erat
    -0.07
    POSITIVE LOGITS
     vs
    0.07
    otis
    0.07
     Wiener
    0.06
    æį·
    0.06
     unknow
    0.06
    *
    0.06
    è¿·
    0.06
     Bhar
    0.06
    imation
    0.06
    æĺ§
    0.06
    Activations Density 0.007%

    No Known Activations