© 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. 28469
    Prev
    Next
    INDEX
    Explanations

    database or requirement

    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
    èݱ德
    -0.08
    eix
    -0.08
    imar
    -0.07
    arella
    -0.07
    efa
    -0.07
    :error
    -0.07
     narrowly
    -0.07
    缸åħ³èµĦ讯
    -0.07
    иÑģÑĤо
    -0.07
    echa
    -0.07
    POSITIVE LOGITS
    æĴ
    0.09
    æį¢
    0.07
    ξι
    0.07
    ONG
    0.07
    /*/
    0.07
    RACT
    0.06
    urr
    0.06
    ãĨ
    0.06
    usus
    0.06
    æŃ¤èµ·å½¼
    0.06
    Activations Density 0.001%

    No Known Activations