© 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. 12673
    Prev
    Next
    INDEX
    Explanations

    arbitrary graph

    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
    appelle
    -0.08
    åĽłä¸ºæ²¡æľī
    -0.07
     poÅĽred
    -0.07
    å½±
    -0.06
    ONSE
    -0.06
     appe
    -0.06
    åĿª
    -0.06
    åĽłäºº
    -0.06
    enstein
    -0.06
    arges
    -0.06
    POSITIVE LOGITS
    ä»»æĦı
    0.09
    æıIJä¾Ľä»»ä½ķ
    0.09
    éļı便
    0.08
    ç»´å¥ĩ
    0.08
     arbitrary
    0.08
     sufficiently
    0.08
    ä»»ä½ķä¿Ŀè¯ģ
    0.08
    ä»Ģä¹Īæł·çļĦ
    0.08
    åıªè¦ģæĺ¯
    0.08
    Brun
    0.08
    Activations Density 0.025%

    No Known Activations