© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46574
    Prev
    Next
    INDEX
    Explanations

    actions that have been completed

    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
    ordat
    -0.07
    -types
    -0.07
    ydd
    -0.06
    起家
    -0.06
    antal
    -0.06
    elv
    -0.06
    keit
    -0.06
    缸åħ³æĥħåĨµ
    -0.06
    ä¸İåħ±
    -0.06
     renc
    -0.06
    POSITIVE LOGITS
     вами
    0.12
    /generated
    0.12
    å·²ä¹ħçļĦ
    0.11
     ëĮĢë¡ľ
    0.11
    ä¸įä¹ħçļĦ
    0.10
    并ç»ı
    0.10
    ëĮĢë¡ľ
    0.10
    owitz
    0.09
     ÐĴами
    0.09
    epend
    0.09
    Activations Density 0.173%

    No Known Activations