© 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. 41713
    Prev
    Next
    INDEX
    Explanations

    options or alternatives

    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
    å¦Ĥåħ¶
    -0.07
    æĺ¯åħ¶
    -0.07
    å®ĥæīĢ
    -0.07
     decoded
    -0.06
    ä¹ĺ
    -0.06
    缸éļı
    -0.06
     unfolding
    -0.06
    raf
    -0.06
    gram
    -0.06
     unravel
    -0.06
    POSITIVE LOGITS
     alternatives
    0.15
    é¦ĸéĢī
    0.12
     alternatif
    0.11
     Altern
    0.11
     alternative
    0.11
    _altern
    0.11
    Alternative
    0.11
    éģ¸æĬŀèĤ¢
    0.11
    å¤ĩéĢī
    0.11
    alternative
    0.11
    Activations Density 0.418%

    No Known Activations