© 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. 48038
    Prev
    Next
    INDEX
    Explanations

    each pair

    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
    å°ı妹
    -0.08
    actics
    -0.07
    åĩłç»ı
    -0.07
    коли
    -0.07
    Ùĥت
    -0.07
     inqu
    -0.07
    icates
    -0.07
    ÄĻcie
    -0.07
     symp
    -0.06
    ллÑı
    -0.06
    POSITIVE LOGITS
    åľ¨æ¯ı个
    0.13
    åľ¨åIJĦ
    0.13
    çĶ±åIJĦ
    0.11
    对æīĢæľī
    0.10
    emap
    0.10
    让è¿ĻäºĽ
    0.10
    对åIJĦ
    0.10
    å°ĨæīĢæľī
    0.10
    éģį
    0.10
    æĬĬæīĢæľī
    0.10
    Activations Density 0.337%

    No Known Activations