© 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. 28879
    Prev
    Next
    INDEX
    Explanations

    biological structures

    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
    etr
    -0.07
    éģį
    -0.07
    æĿİåĺī
    -0.06
    ÃŃv
    -0.06
    erc
    -0.06
    à¸Ńยà¹Īาà¸ĩà¹Ħร
    -0.06
    estr
    -0.06
     something
    -0.06
    emp
    -0.06
    /upload
    -0.06
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸Ģæł·
    0.11
    ä¹Łæĺ¯å¦ĤæѤ
    0.10
    ä¹Łä¸Ģæł·
    0.09
    亦çĦ¶
    0.09
    åĪĻéľĢè¦ģ
    0.09
    åĪĻ以
    0.08
    åĪĻå°Ĩ
    0.08
    åĪĻè¦ģ
    0.08
    _THROW
    0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
    Activations Density 0.060%

    No Known Activations