© 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. 64297
    Prev
    Next
    INDEX
    Explanations

    places of business

    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
    åī¯åĮºéķ¿
    -0.08
    åī¯ç»Ħéķ¿
    -0.08
    -speaking
    -0.08
    åī¯å¸Ĥéķ¿
    -0.08
    steller
    -0.08
    è¿ĽåºĹ
    -0.08
    ä¸įæ¸Ŀ
    -0.07
    ãģ®ãĥĽãĥĨãĥ«
    -0.07
    宫åĨħ
    -0.07
    /logo
    -0.07
    POSITIVE LOGITS
    çŃīåľºæīĢ
    0.12
    à¹ģหà¹Īà¸ĩà¸Ļีà¹ī
    0.12
    æŀĹç«ĭ
    0.11
    éĩĮçļĦ
    0.10
    åĨħçļĦ
    0.10
    æŧåĿĢ
    0.09
    åħ§çļĦ
    0.09
    裡çļĦ
    0.09
    çŃīåľ°çļĦ
    0.09
    éŨåı£
    0.09
    Activations Density 0.543%

    No Known Activations