© 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. 26701
    Prev
    Next
    INDEX
    Explanations

    proof and derivation

    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
    æĬĺ
    -0.07
     Williamson
    -0.07
    igar
    -0.07
     Tuch
    -0.07
    rug
    -0.07
    å´İ
    -0.06
    icolo
    -0.06
    ä¹Łå°±
    -0.06
    æķĪ
    -0.06
    èĸª
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºåľ¨
    0.09
     Proof
    0.08
    Proof
    0.08
    åĽłä¸º
    0.08
     proof
    0.08
    æĥ³ä¸Ģæĥ³
    0.08
    ationale
    0.08
    æݨ导
    0.08
     derivation
    0.08
    为ä»Ģä¹Īåij¢
    0.07
    Activations Density 0.087%

    No Known Activations