© 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. 29135
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    并ç»ı
    -0.08
    :$
    -0.07
    !),
    -0.07
    å¿ĥçĶĺ
    -0.07
    ):(
    -0.07
    ç«£
    -0.07
    ools
    -0.07
    ãĢģ
    -0.07
    å®īåIJī
    -0.07
    lood
    -0.07
    POSITIVE LOGITS
    ãĢĤ
    0.08
    áŁĶ
    0.07
    çŃīå¾ħ
    0.07
    omes
    0.07
    æĺµ
    0.07
    å¦Ĥèĭ¥
    0.06
    ạn
    0.06
    istor
    0.06
    uern
    0.06
     wait
    0.06
    Activations Density 0.001%

    No Known Activations