© 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. 39321
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    æĽ´æĸ°æĹ¥æľŁ
    -0.09
    uation
    -0.09
    è¿ĶåĽŀé¦ĸ页
    -0.08
    ior
    -0.08
    缸åħ³éĹ®çŃĶ
    -0.08
    iosis
    -0.08
    注æĦıå®īåħ¨
    -0.08
    ibal
    -0.08
    СпаÑĢÑĤа
    -0.07
    ersist
    -0.07
    POSITIVE LOGITS
    “
    0.08
    fait
    0.08
    oles
    0.08
    çļĦå°±æĺ¯
    0.08
    æŃ¤èµ·
    0.08
    ly
    0.07
    æŁIJç§į
    0.07
    Ĥ
    0.07
    ä¸Ģå®ļçļĦ
    0.07
    ÙħÙĨد
    0.07
    Activations Density 0.002%

    No Known Activations