© 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. 60926
    Prev
    Next
    INDEX
    Explanations

    redundant or pointless

    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
    æīĢæľª
    -0.08
    ungsweise
    -0.07
    avas
    -0.07
    rlen
    -0.07
    ÑħÑĸ
    -0.07
    SimpleName
    -0.07
    guards
    -0.07
    gericht
    -0.07
    wick
    -0.07
    chas
    -0.07
    POSITIVE LOGITS
     redundant
    0.12
     inutile
    0.12
    èµĺ
    0.11
    åĨĹä½Ļ
    0.11
    å¤ļä½Ļ
    0.10
     unnecessary
    0.10
    å¾Ĵ
    0.10
    浪费
    0.10
    ä¸įå¿ħè¦ģ
    0.09
    è´ħ
    0.09
    Activations Density 0.038%

    No Known Activations