© 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. 33750
    Prev
    Next
    INDEX
    Explanations

    month/year followed by action

    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
    æµ®çĶŁ
    -0.07
    缺å°ij
    -0.06
    lsi
    -0.06
    TS
    -0.06
    å¸Į
    -0.06
    odate
    -0.06
    æĺ¯åIJ¦ç¬¦åIJĪ
    -0.06
    isers
    -0.06
    æĢķ
    -0.06
    缺ä¹ı
    -0.06
    POSITIVE LOGITS
    éĩı身å®ļåĪ¶
    0.08
    ologa
    0.07
    सार
    0.07
    ']]['
    0.07
    ĶĦ
    0.06
     indeed
    0.06
     juntamente
    0.06
    å¹´å°Ĩ
    0.06
    aian
    0.06
     ëįķë¶ĦìĹIJ
    0.06
    Activations Density 0.001%

    No Known Activations