© 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. 1946
    Prev
    Next
    INDEX
    Explanations

    integer and number properties

    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
    inar
    -0.09
    æºIJåľ°
    -0.08
    elt
    -0.08
    å¾ĢæľŁåĽŀ顾
    -0.08
    elles
    -0.07
    iveness
    -0.07
     vá»ijn
    -0.07
    家å®Ŀ
    -0.07
    anas
    -0.07
     Held
    -0.07
    POSITIVE LOGITS
     multiples
    0.07
    à¹Ĩ
    0.07
    -number
    0.07
    ifiable
    0.07
    æĪĸä¸į
    0.06
    arkin
    0.06
    ajib
    0.06
    ä¸į移
    0.06
    -ish
    0.06
    vable
    0.06
    Activations Density 0.006%

    No Known Activations