© 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. 27502
    Prev
    Next
    INDEX
    Explanations

    density, congestion, richness, frequency

    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
    æĹłæŀģ
    -0.08
    åıĮ缮
    -0.07
    vara
    -0.07
    çľ¼çĿģ
    -0.07
    áĥĶáĥijáĥĺáĥĹ
    -0.07
    egni
    -0.07
     unkompl
    -0.07
    _least
    -0.07
    è·¯ä¸ľ
    -0.07
    uliar
    -0.07
    POSITIVE LOGITS
    å¯Ĩ度
    0.11
     density
    0.11
     densities
    0.10
     crow
    0.09
    -density
    0.09
     Density
    0.09
    density
    0.09
    æĭ¥æĮ¤
    0.09
    é«ĺå¯Ĩ度
    0.08
     congestion
    0.08
    Activations Density 0.015%

    No Known Activations