© 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. 41430
    Prev
    Next
    INDEX
    Explanations

    lithography, cells, vein grafts

    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
    bey
    -0.07
    æł¹æį®å®ŀéĻħæĥħåĨµ
    -0.07
     tol
    -0.07
    à¹ĥà¸Ļà¸ģลุà¹Īม
    -0.07
    åĩºä¹İ
    -0.07
    ç½ķè§ģçļĦ
    -0.07
    è¨Ģä¹ĭ
    -0.07
     Barg
    -0.06
    å°±åľ¨è¿ĻæŶ
    -0.06
     gadgets
    -0.06
    POSITIVE LOGITS
    çĶ¨äºİ
    0.22
    çĶ¨æĸ¼
    0.17
    à¹ĥà¸Ĭà¹īà¹ĥà¸Ļà¸ģาร
    0.15
    çĶ¨æĿ¥
    0.15
    主è¦ģçĶ¨äºİ
    0.14
    åı¯çĶ¨äºİ
    0.14
    çĶ¨äºİæ²»çĸĹ
    0.14
    çĶ¨ä»¥
    0.13
    å¹¿æ³ĽçĶ¨äºİ
    0.13
    çĶ¨åľ¨
    0.13
    Activations Density 0.907%

    No Known Activations