© 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. 43491
    Prev
    Next
    INDEX
    Explanations

    different than

    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¸įå¿ĺ
    -0.09
    çļĦéĥ½æĺ¯
    -0.08
    igaret
    -0.08
    åĸľéĹ»
    -0.08
    ä¸įèĥ½è¶ħè¿ĩ
    -0.08
    ä¸įåĬł
    -0.08
    åħ¬èĭ±
    -0.08
    æľĢéļ¾
    -0.08
    erno
    -0.07
    ument
    -0.07
    POSITIVE LOGITS
     than
    0.13
    than
    0.13
     altogether
    0.12
    Than
    0.12
    _than
    0.11
     нежели
    0.11
    -than
    0.11
     Than
    0.11
     THAN
    0.10
    å®Įåħ¨ä¸įåIJĮçļĦ
    0.10
    Activations Density 0.108%

    No Known Activations