© 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. 63628
    Prev
    Next
    INDEX
    Explanations

    chromatography and filtration techniques

    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
    æĮij
    -0.08
    并åıij
    -0.07
    æ¯ıå¹³æĸ¹ç±³
    -0.07
    åŀĤ缴
    -0.07
    orf
    -0.07
     antim
    -0.06
    å°
    -0.06
     strtoupper
    -0.06
    rog
    -0.06
     math
    -0.06
    POSITIVE LOGITS
    èse
    0.08
    绿èī²éĢļéģĵ
    0.08
    æĺĵçĩĥæĺĵçĪĨ
    0.07
    天çİĭ
    0.07
     disclosed
    0.07
    enstein
    0.07
    为åħĪ
    0.07
    çļĦåĬ¨åĬĽ
    0.07
    åħĪ导
    0.07
    解æ¯Ĵ
    0.07
    Activations Density 0.008%

    No Known Activations