© 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. 11342
    Prev
    Next
    INDEX
    Explanations

    write as integral or inequalities

    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
    quential
    -0.07
    educt
    -0.07
    賦
    -0.07
    uris
    -0.07
     imm
    -0.06
     Ende
    -0.06
    ака
    -0.06
    bum
    -0.06
    å¦ĤæѤçļĦ
    -0.06
    okit
    -0.06
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.09
     expres
    0.09
     gá»įn
    0.09
    ouw
    0.08
     expresses
    0.08
     expressing
    0.07
    奨
    0.07
    å¾ĹæĽ´
    0.07
     expressions
    0.07
    å¾Īæ¸ħæ¥ļ
    0.07
    Activations Density 0.008%

    No Known Activations