© 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. 10006
    Prev
    Next
    INDEX
    Explanations

    fixed points and periodic phenomena

    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
     brabant
    -0.07
     ØŃا
    -0.07
     اÙĦØŃا
    -0.07
    å«ģ
    -0.07
     specs
    -0.07
    æijĺç¼ĸ
    -0.06
    charg
    -0.06
    junk
    -0.06
    rex
    -0.06
    chants
    -0.06
    POSITIVE LOGITS
    ä¸įåĬ¨
    0.10
    ä¸įåĭķ
    0.08
    ="__
    0.08
    chaft
    0.08
    lder
    0.07
    enschaft
    0.07
    åĦ¿æŶ
    0.07
    nor
    0.07
    rest
    0.07
    çķĻå¿ĥ
    0.06
    Activations Density 0.005%

    No Known Activations