© 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. 61132
    Prev
    Next
    INDEX
    Explanations

    .gnu licenses

    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
    IDI
    -0.08
    çĭ¬
    -0.08
    ä¹ĭæŃĮ
    -0.08
    oucher
    -0.07
    ocomplete
    -0.07
    icles
    -0.07
    ouchers
    -0.07
    å§Ĩæĸ¯
    -0.07
    tige
    -0.07
     geçmiÅŁ
    -0.07
    POSITIVE LOGITS
     McB
    0.06
    perhaps
    0.06
     ↵↵
    0.06
    å°ĺåŁĥ
    0.06
    åĿĬ
    0.06
     Ultimately
    0.06
    amenta
    0.06
    ane
    0.06
    ابÙĩ
    0.06
    omb
    0.06
    Activations Density 0.001%

    No Known Activations