© 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. 43167
    Prev
    Next
    INDEX
    Explanations

    puzzle solving

    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
    ognito
    -0.09
    ocere
    -0.08
    arana
    -0.08
    onald
    -0.08
     sano
    -0.08
    oraf
    -0.08
    ÏĢÏī
    -0.08
    usc
    -0.08
    ementer
    -0.08
    Äħtek
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.10
    ä¸įäºĨçļĦ
    0.09
    olution
    0.08
    .solve
    0.08
    es
    0.07
    ধান
    0.07
    iette
    0.07
    olving
    0.07
    ä¸įäºĨäºĨ
    0.06
    as
    0.06
    Activations Density 0.022%

    No Known Activations