© 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. 26945
    Prev
    Next
    INDEX
    Explanations

    more, read more, show more

    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
    SEQ
    -0.07
    winkel
    -0.07
    upan
    -0.07
     ê³¼
    -0.06
    ÑĩиÑģ
    -0.06
    æ´½
    -0.06
    è¿ij两年
    -0.06
    otty
    -0.06
    天ä¹ĭ
    -0.06
    jid
    -0.06
    POSITIVE LOGITS
    åĪ©çī©
    0.08
    sandbox
    0.08
    注æĦıä¼ijæģ¯
    0.07
    çĶº
    0.07
     nghiá»ĩp
    0.07
    omobil
    0.07
     Bamb
    0.07
    غد
    0.07
    .definition
    0.07
    andbox
    0.06
    Activations Density 0.017%

    No Known Activations