© 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. 963
    Prev
    Next
    INDEX
    Explanations

    scaling normalized to functions

    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
    ç¼ĿåIJĪ
    -0.08
    isin
    -0.07
    hlas
    -0.07
    acula
    -0.07
    æī¦
    -0.07
     pickups
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    oton
    -0.07
    Promise
    -0.07
    å¤ĸç§ijæīĭæľ¯
    -0.07
    POSITIVE LOGITS
     scaled
    0.11
    scaled
    0.11
    å½Ĵ
    0.10
     scaling
    0.09
     normalized
    0.09
    Scaled
    0.09
    caled
    0.09
    æłĩåĩĨåĮĸ
    0.09
    ä¸įå½Ĵ
    0.09
    Scaling
    0.08
    Activations Density 0.028%

    No Known Activations