© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46681
    Prev
    Next
    INDEX
    Explanations

    names following punctuation

    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
    adem
    -0.08
    æĪij为群ä¼ĹåĬŀå®ŀäºĭ
    -0.08
    ä¼ģä¸ļèį£èªī
    -0.07
    ova
    -0.07
    кÑĤÑĸ
    -0.07
    stown
    -0.07
    -less
    -0.07
    еÑĤе
    -0.07
    leveland
    -0.07
    ä»Ģä¹Īéĥ½æ²¡
    -0.07
    POSITIVE LOGITS
    æī¹
    0.07
    æĺŃ
    0.07
    urit
    0.06
    大æŀĹ
    0.06
    à¸Ĭัย
    0.06
    egis
    0.06
    çĶ»
    0.06
    arring
    0.06
    _GENER
    0.06
    acco
    0.06
    Activations Density 0.001%

    No Known Activations