© 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. 24891
    Prev
    Next
    INDEX
    Explanations

    variable or networks

    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
     tim
    -0.07
    çĭĤ
    -0.06
    urus
    -0.06
    ç«ĸ
    -0.06
     Rhe
    -0.06
     mise
    -0.06
    Frank
    -0.06
     cast
    -0.06
     coll
    -0.05
     Tim
    -0.05
    POSITIVE LOGITS
     inicialmente
    0.09
    æľĢåĪĿçļĦ
    0.09
     pierw
    0.08
    æľ¬æĿ¥æĺ¯
    0.08
    malink
    0.08
    *&
    0.08
    -bot
    0.08
    hea
    0.08
    utsch
    0.08
    ucus
    0.08
    Activations Density 0.392%

    No Known Activations