© 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. 55309
    Prev
    Next
    INDEX
    Explanations

    ion exchange, chromatography, cracking

    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
     procur
    -0.08
    steller
    -0.08
    éĽĨä¸Ńæķ´æ²»
    -0.07
    æ·¡æ·¡
    -0.07
    éc
    -0.07
    æģĻ
    -0.07
    æijĨ
    -0.07
    à§Ī
    -0.07
    åĪ©çī©
    -0.07
    otech
    -0.06
    POSITIVE LOGITS
    ä¸įæĶ¹
    0.08
    Na
    0.08
     Na
    0.08
    CCC
    0.08
    ç²Ĵ
    0.08
    åĽ½å¼º
    0.07
     sodium
    0.07
    Õ¡Õ¶
    0.07
    é¦Ĵ头
    0.07
    Ỽ
    0.07
    Activations Density 0.012%

    No Known Activations