© 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. 33496
    Prev
    Next
    INDEX
    Explanations

    analytic expressions

    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
    说好
    -0.07
    chino
    -0.07
    idio
    -0.07
    涵
    -0.07
    æĪijåIJij
    -0.07
     Dagger
    -0.06
    ׼×ķף
    -0.06
    akang
    -0.06
     Paste
    -0.06
    ENSE
    -0.06
    POSITIVE LOGITS
     simpl
    0.09
     simplify
    0.09
     analy
    0.09
     simplest
    0.09
    æĺĵäºİ
    0.08
     algebra
    0.08
     easiest
    0.08
    otis
    0.08
     bekend
    0.08
     Simpl
    0.08
    Activations Density 0.087%

    No Known Activations