© 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. 28050
    Prev
    Next
    INDEX
    Explanations

    causing consequences

    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
    æķ°æį®çºłéĶĻ
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    为äºĨ让
    -0.08
    ients
    -0.08
    å¦Ĥèį¼
    -0.08
     ÑĩÑĤоб
    -0.08
    acket
    -0.07
    ä¹ĥ
    -0.07
    еÑģÑģи
    -0.07
    emergen
    -0.07
    POSITIVE LOGITS
     further
    0.08
    使å¾Ĺ
    0.08
     effectively
    0.08
    使åħ¶
    0.08
    使ä»ĸ
    0.07
     creating
    0.07
     necess
    0.07
     making
    0.07
    使æĪij
    0.07
    使æĪij们
    0.07
    Activations Density 0.171%

    No Known Activations