© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    class or type

    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
    ä¸įæIJŀ
    -0.07
    UB
    -0.07
    ropa
    -0.07
    åľ¨åħ¶
    -0.07
    åĮ¹
    -0.07
    ohan
    -0.07
    cit
    -0.07
    åĩıè´Ł
    -0.07
    åijµ
    -0.06
    æīĵå¾Ĺ
    -0.06
    POSITIVE LOGITS
    engeance
    0.08
     protagon
    0.07
    并åħ·æľī
    0.07
    .Marshal
    0.07
    å®ĥ们æĺ¯
    0.06
    å¼Ģåıij建设
    0.06
    ä½łä»¬æĺ¯
    0.06
    edig
    0.06
    ä¸ĩå¹´
    0.06
    æļĩ
    0.06
    Activations Density 0.761%

    No Known Activations