© 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. 43733
    Prev
    Next
    INDEX
    Explanations

    information about

    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
    er
    -0.11
    ounge
    -0.10
    zelf
    -0.10
    erer
    -0.10
    erio
    -0.10
    äºĨèĩªå·±çļĦ
    -0.10
    æĪĸå¤ļ个
    -0.10
     einzigen
    -0.10
    ยัà¸ģษà¹Į
    -0.09
    ยà¹Į
    -0.09
    POSITIVE LOGITS
    Ùĭ
    0.11
    ção
    0.11
    ation
    0.10
    lement
    0.09
    ़
    0.09
    an
    0.08
    åħ¶
    0.08
    ed
    0.08
    ÑİÑĤ
    0.08
    ic
    0.08
    Activations Density 0.079%

    No Known Activations