© 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. 39682
    Prev
    Next
    INDEX
    Explanations

    numbers around parentheses

    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
    å°ģ
    -0.07
    è·µ
    -0.06
    är
    -0.06
    _if
    -0.06
    æĺ¯ä»¥
    -0.06
    åıijæĸĩ
    -0.06
    FieldValue
    -0.06
    ä¸įä¼ļåĽłä¸º
    -0.06
    elle
    -0.05
    assi
    -0.05
    POSITIVE LOGITS
    -toggle
    0.08
     either
    0.08
    yleft
    0.08
    ä»»ä½ķè´¹çĶ¨
    0.08
    ä¹ĭæĢ¥
    0.08
    chap
    0.08
    ä¸įåIJĮæŶ
    0.08
    æ¼Ĥ
    0.08
     Celebrity
    0.07
    æīĢ欲
    0.07
    Activations Density 0.033%

    No Known Activations