© 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. 56542
    Prev
    Next
    INDEX
    Explanations

    how do i

    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
    ulos
    -0.07
    ately
    -0.06
    éļħ
    -0.06
    inho
    -0.06
     legislat
    -0.06
    ighth
    -0.06
    ä»Ĭ天è¦ģ
    -0.06
    ivism
    -0.06
    óc
    -0.06
    æīĭæľºä¸Ĭ
    -0.06
    POSITIVE LOGITS
    ãĥªãĤ¨
    0.09
    ä»Ģä¹Īåij¢
    0.08
    loge
    0.07
    arz
    0.07
    Äħtek
    0.07
    ä¸įç®Ģåįķ
    0.07
    æľīæĿĥä¿ĿçķĻ
    0.07
    ער
    0.07
    ftware
    0.07
    epro
    0.07
    Activations Density 0.012%

    No Known Activations