© 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. 58148
    Prev
    Next
    INDEX
    Explanations

    NOT NULL, expect

    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
    è¿ĺåı¯ä»¥åľ¨
    -0.09
     Cousins
    -0.07
    azel
    -0.07
    åŃļ
    -0.07
    ackle
    -0.06
    Occurrences
    -0.06
    ìĸ´ëĵ¤
    -0.06
    ×Ļ×Ļ×Ŀ
    -0.06
    åīį沿
    -0.06
    çļĦåīį沿
    -0.06
    POSITIVE LOGITS
    èĩ³å°ij
    0.11
     almeno
    0.11
    èĩ³å°ijè¦ģ
    0.10
    èĩ³å°ijæľī
    0.10
    èĩ³å°ijåľ¨
    0.10
     atleast
    0.09
    缺ä¸Ģä¸įåı¯
    0.09
    ban
    0.08
    ä¿Ŀè¯ģåħ¶
    0.08
    èµ·çłģ
    0.08
    Activations Density 0.079%

    No Known Activations