© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37779
    Prev
    Next
    INDEX
    Explanations

    named entities and specific terms

    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
    rawat
    -0.09
    ugend
    -0.09
    UnderTest
    -0.08
    å°±æĺ¯äºĨ
    -0.08
    ì¤
    -0.08
    peg
    -0.08
    /********
    -0.08
    _BOTH
    -0.08
    endu
    -0.08
    adres
    -0.08
    POSITIVE LOGITS
    åĴĮæĹł
    0.06
    zew
    0.06
    aux
    0.06
    ç½Ĺ纳
    0.05
    uet
    0.05
    rost
    0.05
     apl
    0.05
    R
    0.05
    entially
    0.05
    åıį対
    0.05
    Activations Density 1.035%

    No Known Activations