© 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. 7649
    Prev
    Next
    INDEX
    Explanations

    math and numbers after section headers

    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
    g
    -0.07
    æ¸łéģĵ
    -0.07
    f
    -0.07
    ir
    -0.06
    argin
    -0.06
    itiv
    -0.06
    å³
    -0.06
    asking
    -0.06
     prod
    -0.06
    åİŁ
    -0.06
    POSITIVE LOGITS
    æĢ»ä½ĵè¦ģæ±Ĥ
    0.08
    thur
    0.08
    zach
    0.08
    æĪijåĮº
    0.08
    æĸ°åĬłåĿ¡
    0.08
    _ctxt
    0.08
    æľĢéĩįè¦ģçļĦæĺ¯
    0.08
    elsey
    0.08
    ä¾ĽåºĶä¿¡æģ¯
    0.08
    ungg
    0.08
    Activations Density 0.002%

    No Known Activations