© 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. 33645
    Prev
    Next
    INDEX
    Explanations

    package identifiers and file paths

    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
    md
    -0.06
    azo
    -0.06
    -mf
    -0.06
    æĹ©
    -0.06
    ::
    -0.06
    áĥ«
    -0.06
    å®ļ
    -0.06
    è´¯
    -0.06
     ÙĨاÙģ
    -0.05
    ennon
    -0.05
    POSITIVE LOGITS
    ENE
    0.08
    orman
    0.08
    ä½łåĨį
    0.08
    bdb
    0.07
    Ñģлан
    0.07
    cott
    0.07
    åı¦å¤ĸä¸Ģ个
    0.07
     yourselves
    0.07
    ityEngine
    0.07
    itados
    0.07
    Activations Density 0.024%

    No Known Activations