© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63821
    Prev
    Next
    INDEX
    Explanations

    mathematical extensions and equations

    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
    æĭĹ
    -0.08
    .capitalize
    -0.07
    ertools
    -0.06
     tan
    -0.06
    vary
    -0.06
     recal
    -0.06
     r
    -0.06
    .readLine
    -0.06
     gut
    -0.06
     activeClassName
    -0.06
    POSITIVE LOGITS
    æī©å±ķ
    0.11
    æī©åħħ
    0.09
    èĨ¨
    0.09
     expands
    0.09
    æĭĵå±ķ
    0.08
     expanded
    0.08
    ancier
    0.08
    å¤įåIJĪ
    0.08
    lift
    0.08
    æī©
    0.07
    Activations Density 0.032%

    No Known Activations