© 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. 49913
    Prev
    Next
    INDEX
    Explanations

    local server-based

    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
    /ajax
    -0.07
    åİŁä»¶åıĬ
    -0.07
    acher
    -0.07
    лÑıли
    -0.07
    æĸ©èİ·
    -0.07
    inent
    -0.07
    eppe
    -0.07
    æĶ¶èµ·
    -0.06
    缴æİ¥å°Ĩ
    -0.06
    ноÑģÑıÑĤ
    -0.06
    POSITIVE LOGITS
    亦çĦ¶
    0.11
     thereafter
    0.10
    åĪĻ
    0.09
     zaÅĽ
    0.09
     thereof
    0.09
     же
    0.09
    åį´
    0.08
     consequently
    0.08
    为è¾ħ
    0.08
    åį´ä¸įçŁ¥éģĵ
    0.08
    Activations Density 0.070%

    No Known Activations