© 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. 47183
    Prev
    Next
    INDEX
    Explanations

    else or other values

    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
    åŃľåŃľ
    -0.08
    Äįa
    -0.07
    ISTR
    -0.07
    ÏĪε
    -0.07
    æģ¬
    -0.07
    íĭĢ
    -0.07
    isko
    -0.07
    onte
    -0.07
     ÑħваÑĤаеÑĤ
    -0.07
    iddleware
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.12
    æ¯Ķå¦Ĥ
    0.11
    æ¯Ķå¦Ĥ说
    0.09
    èѬå¦Ĥ
    0.09
    ãģŁãģ¨ãģĪãģ°
    0.09
     ÐĿапÑĢимеÑĢ
    0.09
     напÑĢимеÑĢ
    0.08
    ä¾ĭãģĪãģ°
    0.08
    诸å¦Ĥ
    0.08
    æ¯Ķå¦Ĥåľ¨
    0.08
    Activations Density 0.021%

    No Known Activations