© 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. 64333
    Prev
    Next
    INDEX
    Explanations

    ending statements

    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
     напÑĢимеÑĢ
    -0.08
    µľ
    -0.08
    ãĥ£
    -0.07
     totiž
    -0.07
    inkt
    -0.07
    ä¸ĢæŶ
    -0.07
    вÑıз
    -0.07
    éf
    -0.07
    ä¾ĭå¦Ĥ
    -0.07
    æĸ°é«ĺ
    -0.07
    POSITIVE LOGITS
    Ùĭ
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.07
    o
    0.07
    uri
    0.07
    ož
    0.07
    å°Ķå¾·
    0.07
    о
    0.07
    icismo
    0.06
    ÙİÙij
    0.06
    Ī
    0.06
    Activations Density 0.014%

    No Known Activations