© 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. 38361
    Prev
    Next
    INDEX
    Explanations

    matter and energy

    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
    elingen
    -0.08
    estre
    -0.07
    æīĭçĶµ
    -0.07
     má»±c
    -0.07
    champ
    -0.07
    zett
    -0.07
    ofilm
    -0.07
    -lang
    -0.07
    кок
    -0.07
    หว
    -0.07
    POSITIVE LOGITS
    /material
    0.10
    ity
    0.09
    istic
    0.08
     اÙĦخاÙħ
    0.08
    ä¸ĸçķĮçļĦ
    0.08
    è´¨çļĦ
    0.08
    ä¸įçģŃ
    0.07
    itious
    0.07
    æħ¾
    0.07
    /
    0.07
    Activations Density 0.010%

    No Known Activations