© 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. 25238
    Prev
    Next
    INDEX
    Explanations

    subtracting numbers or equations

    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
    çļĦåIJĹ
    -0.09
    æĪijåIJĹ
    -0.08
    åIJĹ
    -0.08
    çļĦäºĭäºĨ
    -0.08
    ().
    -0.07
    ,but
    -0.07
    "';
    -0.07
    åĽłä¸ºåıªæľī
    -0.07
    ä½Ĩä½ł
    -0.07
    ä½Ĩå¦Ĥæŀľ
    -0.07
    POSITIVE LOGITS
    ä¸įéļ¾
    0.10
     ÙģØ¥ÙĨ
    0.10
     ÙģØ¥ÙĨÙĩ
    0.09
     λοι
    0.09
    ä½ľåĪĻ
    0.08
    åı¯çŁ¥
    0.08
     ëĶ°ë¥´ë©´
    0.08
     maka
    0.08
    halen
    0.08
     ìĤ¬ìļ©íķĺë©´
    0.08
    Activations Density 0.029%

    No Known Activations