© 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. 21375
    Prev
    Next
    INDEX
    Explanations

    limitations and bounds

    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
    ä¾ĭè¡Į
    -0.09
    æĮ¯åįİ
    -0.08
     routine
    -0.08
    routine
    -0.08
     rutin
    -0.08
    stash
    -0.07
    strup
    -0.07
    oard
    -0.07
    å¾Ģ常
    -0.07
    常è§Ħ
    -0.07
    POSITIVE LOGITS
     achievable
    0.09
     limits
    0.09
     theoretical
    0.09
     theoret
    0.09
    ä¸ĬéĻIJ
    0.08
     bound
    0.08
     ideal
    0.08
    çIJĨ论ä¸Ĭ
    0.08
     attain
    0.08
     limit
    0.08
    Activations Density 0.019%

    No Known Activations