© 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. 1998
    Prev
    Next
    INDEX
    Explanations

    expected output

    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
    rought
    -0.07
    好åĥıåľ¨
    -0.07
    ç¾ŀ
    -0.07
    æľ¬æĬ¥è®¯
    -0.07
    _DECLARE
    -0.07
    èį
    -0.07
    ông
    -0.06
     somehow
    -0.06
    Depart
    -0.06
    ạ
    -0.06
    POSITIVE LOGITS
     expected
    0.11
    é¢ĦæľŁ
    0.10
    é¢ĦæľŁçļĦ
    0.10
     predictable
    0.10
    expected
    0.10
    çļĦé¢ĦæľŁ
    0.10
    (expected
    0.09
     ìĺĪìĥģ
    0.09
     Expected
    0.09
    .expected
    0.09
    Activations Density 0.047%

    No Known Activations