© 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. 29291
    Prev
    Next
    INDEX
    Explanations

    resides process

    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
    à¹Īาà¸Ļ
    -0.08
    ühr
    -0.08
    aider
    -0.07
    åĮ¹åħĭ
    -0.07
    δÏĮ
    -0.07
    uide
    -0.07
    Matcher
    -0.07
    ģ
    -0.07
    æ¡Ī
    -0.07
    ä¸Ģç³»åĪĹ
    -0.07
    POSITIVE LOGITS
     ÙĪاÙĦتÙĬ
    0.09
    åı«ä»Ģä¹Ī
    0.08
    åı«åģļ
    0.07
     tzv
    0.07
     ÙĪاÙĦØ°ÙĬ
    0.07
    åħ¶ä¹IJ
    0.07
     (`
    0.07
    ç®Ģ称
    0.07
     ones
    0.07
    اÙĪÙĨ
    0.07
    Activations Density 0.530%

    No Known Activations