© 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. 51386
    Prev
    Next
    INDEX
    Explanations

    since epoch

    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
    lbrace
    -0.09
     hüb
    -0.08
    teca
    -0.08
    hetto
    -0.08
    æºī
    -0.08
    MaxLength
    -0.08
     hydrat
    -0.08
    impa
    -0.08
    haj
    -0.08
    æĪIJé¾Ļ
    -0.07
    POSITIVE LOGITS
    ppen
    0.07
     Kelvin
    0.07
    åIJ¯
    0.06
     shut
    0.06
     temperatures
    0.06
     absolute
    0.06
    çĪµ
    0.06
     Mc
    0.06
     universal
    0.06
    Absolute
    0.06
    Activations Density 0.001%

    No Known Activations