© 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. 32355
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives or definitions

    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
    dings
    -0.06
    ä½ij
    -0.06
    zio
    -0.06
    oggles
    -0.06
    çīĩçļĦ
    -0.06
    jó
    -0.06
    añas
    -0.06
     Casal
    -0.06
    å°±åĪ°
    -0.06
    åĮħçļĦ
    -0.05
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.09
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
    ãģĿãģĨãģ§
    0.08
     daarna
    0.07
    ä¸İæĸ¹æ³ķ
    0.07
    éĹ®é¢ĺ导åIJij
    0.07
     ê·¸ëłĩì§Ģ
    0.07
    asty
    0.07
    ä¸įåºĶæ±Ĥ
    0.07
    èĿł
    0.07
    Activations Density 0.343%

    No Known Activations