© 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. 9786
    Prev
    Next
    INDEX
    Explanations

    spatial relationships

    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
    梦å¯IJ以æ±Ĥ
    -0.08
    ãģĦãģį
    -0.08
    jach
    -0.08
    æł©æł©
    -0.08
    æĿijæĿij
    -0.08
    stil
    -0.08
    éģĶ人
    -0.08
     NotFoundException
    -0.07
    icot
    -0.07
    çĶŁè¾ī
    -0.07
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.09
    èĢĮéĿŀ
    0.09
    èĢĮä¸İ
    0.08
     rather
    0.08
    æĿ¥åĨ³å®ļ
    0.08
    ä¸įçľĭ
    0.07
    åľ¨äºİ
    0.07
    ç¨ĭ
    0.07
     geometry
    0.07
    æĺ¯åIJ¦ä¸İ
    0.07
    Activations Density 0.018%

    No Known Activations