© 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. 7513
    Prev
    Next
    INDEX
    Explanations

    thermodynamics or kinetics

    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
    è´¯
    -0.09
    åį¿
    -0.08
    زÙħ
    -0.08
    anty
    -0.07
    貫
    -0.07
    antine
    -0.07
    -Za
    -0.07
    Xd
    -0.07
    éī´
    -0.07
    代è´Ń
    -0.06
    POSITIVE LOGITS
     dictates
    0.08
    èĥľäºİ
    0.08
    ä¹ĭéĢī
    0.08
     overrides
    0.08
    peaker
    0.08
     dictate
    0.08
     override
    0.07
     overriding
    0.07
     dictated
    0.07
    éré
    0.07
    Activations Density 0.003%

    No Known Activations