© 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. 20276
    Prev
    Next
    INDEX
    Explanations

    million views

    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
    iant
    -0.08
    åľ¨é»ij
    -0.07
    lean
    -0.07
    hoven
    -0.07
     chefe
    -0.07
    _each
    -0.07
    dorf
    -0.07
    æľĪèĩ³ä»Ĭ
    -0.07
    arine
    -0.07
    _HAVE
    -0.07
    POSITIVE LOGITS
    à¹Į
    0.07
    ä¸Ģåĩº
    0.07
    çĴIJ
    0.07
    ÑĥÑģÑĤ
    0.07
    ohan
    0.06
    ombs
    0.06
    imes
    0.06
    ths
    0.06
    arked
    0.06
    alc
    0.06
    Activations Density 0.017%

    No Known Activations