© 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. 29451
    Prev
    Next
    INDEX
    Explanations

    result assignment

    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
    abor
    -0.07
    upa
    -0.07
    uki
    -0.07
    æŶæĹ¥
    -0.07
    Wins
    -0.07
    bum
    -0.07
    æĭīæĸ¯
    -0.07
    å§Ķ书记
    -0.06
    orough
    -0.06
    ency
    -0.06
    POSITIVE LOGITS
    æľĢ大
    0.08
    ÑĮÑĤе
    0.07
    ä¹į
    0.07
    å°ļ
    0.06
    åĪ©åīij
    0.06
    деÑĢ
    0.06
    atz
    0.06
    rem
    0.06
    ê²Į
    0.06
    æľĢ大åĮĸ
    0.06
    Activations Density 0.002%

    No Known Activations