© 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. 22040
    Prev
    Next
    INDEX
    Explanations

    assembly registers and instructions

    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
    Õ¡Õ¯
    -0.09
     Wolfs
    -0.08
    å°ıèĬĤ
    -0.07
    /DTD
    -0.07
     administrations
    -0.07
     mse
    -0.07
    çīĻ
    -0.07
    _GAP
    -0.07
    è¿ŁåĪ°
    -0.07
    kez
    -0.07
    POSITIVE LOGITS
    å¯ĦåŃĺåĻ¨
    0.08
     operand
    0.08
     overflowing
    0.07
    常çĶ¨äºİ
    0.07
    _operand
    0.07
    æµ®äºij
    0.07
     citron
    0.06
    è¾ħåĬ©
    0.06
    å¯ĦåŃĺ
    0.06
    -imm
    0.06
    Activations Density 0.049%

    No Known Activations