© 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. 18235
    Prev
    Next
    INDEX
    Explanations

    phrase and idioms

    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
    éħĴå±ĭ
    -0.08
    ä¹ĭåıĪ
    -0.08
    annuncio
    -0.07
    astia
    -0.07
    haps
    -0.07
    æĭ³éģĵ
    -0.07
    [".
    -0.07
    åĩıä»ĵ
    -0.07
    æĹ¥åħ¬å¸ĥ
    -0.07
    èģĨ
    -0.07
    POSITIVE LOGITS
    æĪIJè¯Ń
    0.12
    åħ¸æķħ
    0.10
    形容
    0.09
    æ¢Ĺ
    0.08
    æĿ¥å½¢å®¹
    0.08
     misuse
    0.08
    å¯ĵæĦı
    0.07
     phrase
    0.07
    itis
    0.07
    èĨł
    0.07
    Activations Density 0.016%

    No Known Activations