© 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. 43844
    Prev
    Next
    INDEX
    Explanations

    Roman names and titles

    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
    ä¿IJ
    -0.09
    檸
    -0.09
    å¾ľ
    -0.08
    身ä¸Ĭä¸ĭ
    -0.08
    èķ¾
    -0.08
    墳
    -0.08
    èĮģ
    -0.08
    åı¤å±ĭ
    -0.08
     undermin
    -0.08
    å´Ĺ
    -0.08
    POSITIVE LOGITS
    京å¸Ī
    0.11
    å²ģ
    0.08
    å²ģæŶ
    0.08
    éģĤ
    0.08
    è§ģäºİ
    0.08
    诸
    0.08
    设äºİ
    0.08
    åĻ¨çī©
    0.08
    åľ°æĸ¹
    0.08
    åı·ç§°
    0.08
    Activations Density 0.020%

    No Known Activations