© 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. 26073
    Prev
    Next
    INDEX
    Explanations

    rather 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
    s
    -0.10
    ãģĦãĤĭ
    -0.09
     пожалÑĥй
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    Ñĭ
    -0.08
    erber
    -0.07
    ãģıãģªãģĦ
    -0.07
    inds
    -0.07
    ãģĭãĤĬ
    -0.07
     ê·¸ëŀĺëıĦ
    -0.07
    POSITIVE LOGITS
     than
    0.10
    -than
    0.10
    quam
    0.09
    _than
    0.08
    ä»ħä»ħ
    0.08
    ãģ£ãģ¨
    0.08
    ä»ħä»ħæĺ¯
    0.08
    ÙĨÚ¯
    0.08
    åįķ纯çļĦ
    0.08
    than
    0.08
    Activations Density 0.025%

    No Known Activations