© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    any language

    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
    ÑģÑı
    -0.08
    æŶä¸įæŶ
    -0.07
    ensus
    -0.07
    รร
    -0.07
    ::-
    -0.07
     sheer
    -0.07
    꽤
    -0.07
    acson
    -0.07
    uft
    -0.07
    åĩĿå¿ĥ
    -0.07
    POSITIVE LOGITS
    иÑİ
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    inia
    0.08
    iations
    0.08
    ç±»åŀĭçļĦ
    0.08
    æĦıä¹īä¸Ĭ
    0.08
    toria
    0.08
    iating
    0.08
    ики
    0.08
    cia
    0.07
    Activations Density 0.003%

    No Known Activations