© 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. 41467
    Prev
    Next
    INDEX
    Explanations

    ARK, CT, Clark

    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
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    å¦ĤæŀľæĤ¨æĺ¯
    -0.08
    å¦ĤæŀľæĤ¨å¯¹
    -0.07
    авли
    -0.07
    utely
    -0.07
     behalf
    -0.07
    bject
    -0.07
    wards
    -0.07
    kira
    -0.06
    /or
    -0.06
    POSITIVE LOGITS
    imately
    0.09
    ackson
    0.09
    jenigen
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    exus
    0.08
    agged
    0.08
    schafts
    0.08
    utate
    0.08
    upiter
    0.08
    Activations Density 0.017%

    No Known Activations