© 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. 60948
    Prev
    Next
    INDEX
    Explanations

    punctuation and "unit"

    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
    Relation
    -0.07
    åħ¶å¯¹
    -0.07
    itse
    -0.07
    opp
    -0.07
    æľīè¿Ļæł·çļĦ
    -0.07
     introdu
    -0.06
    uto
    -0.06
     its
    -0.06
    ubbo
    -0.06
    èĩªå·±çļĦ
    -0.06
    POSITIVE LOGITS
    oku
    0.08
    (optional
    0.08
    çļĦè§Ĵèī²
    0.07
    è¿Ļä¸ĢæŃ¥
    0.07
    为äºĨç»Ļ
    0.06
    ä¸İæѤåIJĮæŶ
    0.06
    对ä¸Ĭè¿°
    0.06
    otin
    0.06
    akan
    0.06
     optional
    0.06
    Activations Density 0.010%

    No Known Activations