© 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. 64968
    Prev
    Next
    INDEX
    Explanations

    complex numbers $\mathbb{C}$

    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
    à¹ĥà¸Ī
    -0.08
    <|quad_end|>
    -0.08
    <|box_end|>
    -0.08
    kse
    -0.08
    er
    -0.07
    Ñĭз
    -0.07
    ')+
    -0.07
    اÙĨ
    -0.07
    aine
    -0.07
    ibt
    -0.07
    POSITIVE LOGITS
    0.08
    berman
    0.08
    ancock
    0.07
    ï¸İ
    0.07
    ãĥĭãĥĥãĤ¯
    0.06
    äºĶé¢ľåħŃèī²çļĦ
    0.06
    неÑĤе
    0.06
    antic
    0.06
    лежа
    0.06
    å¬
    0.06
    Activations Density 0.006%

    No Known Activations