© 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. 7990
    Prev
    Next
    INDEX
    Explanations

    implementing something

    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
    ness
    -0.10
    ordin
    -0.10
    ingly
    -0.08
    lettes
    -0.08
    resh
    -0.08
    warts
    -0.08
    İ
    -0.08
    udge
    -0.08
    à¸Ńีà¹ī
    -0.08
    thern
    -0.07
    POSITIVE LOGITS
    repid
    0.09
    ausible
    0.08
    atic
    0.08
    ä¸įäºĨ
    0.08
    agination
    0.08
    æĹłéĹ´
    0.08
     sẵn
    0.07
    ovable
    0.07
    arily
    0.07
    à¹ī
    0.07
    Activations Density 0.046%

    No Known Activations