© 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. 42852
    Prev
    Next
    INDEX
    Explanations

    IOException

    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
    akwa
    -0.08
    akon
    -0.07
    ÏĥÏĩ
    -0.07
    новиÑĩ
    -0.07
    æĸ°ä¹¦
    -0.07
    akter
    -0.07
    ÑĪÑĤа
    -0.07
    éĻ¤äºĨè¦ģ
    -0.07
    שר
    -0.07
     porod
    -0.07
    POSITIVE LOGITS
    å§Ķ
    0.07
    cec
    0.07
    éģĵçļĦ
    0.07
    coa
    0.06
    éģĵ
    0.06
    ÏīÏĤ
    0.06
    åľ°åĿĹ
    0.06
    rames
    0.06
    eno
    0.06
     racked
    0.06
    Activations Density 0.031%

    No Known Activations