© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51884
    Prev
    Next
    INDEX
    Explanations

    typedef struct

    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
    åĩĿ
    -0.07
    å¼Ĥåľ°
    -0.07
    ยาย
    -0.07
    åĺĺ
    -0.07
    ular
    -0.07
    åĨįèµ·
    -0.07
    iblings
    -0.07
    arians
    -0.07
    berger
    -0.07
    ullan
    -0.07
    POSITIVE LOGITS
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.07
    (typeof
    0.06
    CRET
    0.06
     ↵	↵
    0.06
    eya
    0.06
    æĶ¯ä»ĺæĸ¹å¼ı
    0.06
    coffee
    0.06
    /bower
    0.06
     whoever
    0.06
    å¾Ģä¸ĭ
    0.06
    Activations Density 0.083%

    No Known Activations