© 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. 60496
    Prev
    Next
    INDEX
    Explanations

    numerical and approximations

    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
    èģª
    -0.09
    åıĬéĻĦåĬł
    -0.08
    osso
    -0.08
    alloween
    -0.08
    åĪĿä¸ī
    -0.07
    etra
    -0.07
    æħ§èģª
    -0.07
    lessness
    -0.07
    èģ°
    -0.07
    rego
    -0.07
    POSITIVE LOGITS
     approx
    0.10
     approximation
    0.10
    éĢ¼è¿ij
    0.10
     Approx
    0.09
     methods
    0.09
     numerical
    0.09
     Numer
    0.09
     approximate
    0.08
    methods
    0.08
    approx
    0.08
    Activations Density 0.049%

    No Known Activations