© 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. 41311
    Prev
    Next
    INDEX
    Explanations

    with or which

    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
     bid
    -0.07
     kisz
    -0.07
    adaki
    -0.07
    uard
    -0.06
    GetSize
    -0.06
    Sink
    -0.06
    \Facades
    -0.06
    erah
    -0.06
    .getSize
    -0.06
    subs
    -0.06
    POSITIVE LOGITS
    æľīæĽ´å¤ļçļĦ
    0.09
    å·²åħ¨éĥ¨
    0.09
    å·²å°Ĩ
    0.08
    æĺ¯æĬĬ
    0.08
    æĬĬæīĢæľī
    0.08
    -one
    0.08
    configuration
    0.08
    one
    0.07
    æĬĬ
    0.07
    å·²ç»ıå°Ĩ
    0.07
    Activations Density 0.049%

    No Known Activations