© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8937
    Prev
    Next
    INDEX
    Explanations

    letters and 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
    ä¸įèĻļ
    -0.08
    sass
    -0.08
    lok
    -0.07
    常åĬ¡çIJĨäºĭ
    -0.07
    åij½è¿IJ
    -0.07
    ä¸ĵä¸ļå§Ķåijĺä¼ļ
    -0.07
    ä¸ĵå§Ķä¼ļ
    -0.07
    MOVED
    -0.07
    ed
    -0.07
    anea
    -0.07
    POSITIVE LOGITS
    åIJİç»ı
    0.07
    æŃ¤é¡¹
    0.07
    çĶ²åħ¬åı¸
    0.07
    åijĬè¯īäºĨ
    0.07
    æŃ¤æ¬¾
    0.07
    麻éĽĢ
    0.07
    对ä¸Ĭè¿°
    0.07
    è¦ģæ±Ĥåħ¶
    0.06
    äºĮ人
    0.06
    ç±³ç²ī
    0.06
    Activations Density 0.019%

    No Known Activations