© 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. 45014
    Prev
    Next
    INDEX
    Explanations

    (y) or

    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
     INTEG
    -0.09
    åĮĢ称
    -0.07
    æĸ°æŃĮ
    -0.07
    ledo
    -0.07
    ä¸ĵ家ä»ĭç»į
    -0.07
    _consts
    -0.07
    ÑģоÑĢ
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    åĩºæĪĺ
    -0.07
    è°ģçŁ¥
    -0.07
    POSITIVE LOGITS
     tangent
    0.08
     tan
    0.07
    ahas
    0.07
    tan
    0.07
    Stamp
    0.07
    pk
    0.07
     implicitly
    0.07
     auton
    0.06
    oloc
    0.06
     Perkins
    0.06
    Activations Density 0.007%

    No Known Activations