© 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. 40087
    Prev
    Next
    INDEX
    Explanations

    another, others, along, one

    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
    odyn
    -0.08
    hend
    -0.08
    NDER
    -0.07
    太强
    -0.07
    ondi
    -0.07
     Hors
    -0.07
    åħ¨ä½ĵ人åijĺ
    -0.07
    onet
    -0.07
    ailable
    -0.07
    ä¸ĢæĿ¥
    -0.07
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.10
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
    åı¦ä¸ĢåįĬ
    0.10
     another
    0.09
     altrettanto
    0.09
    è¿ĺæľīä»Ģä¹Ī
    0.09
    ãĤĤãģĨ
    0.09
    åı¦å¤ĸä¸Ģ个
    0.09
    åı¦ä¸Ģ个
    0.09
    çŃīåħ¶ä»ĸ
    0.08
    Activations Density 0.020%

    No Known Activations