© 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. 4723
    Prev
    Next
    INDEX
    Explanations

    counting or counts

    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
    Negative Logits
    keit
    -0.11
    er
    -0.10
    pery
    -0.09
    ettings
    -0.09
    -looking
    -0.08
     addCriterion
    -0.08
    ocity
    -0.08
     dÃłng
    -0.08
    ÙĦاء
    -0.08
    itys
    -0.08
    POSITIVE LOGITS
    enance
    0.14
    DownLatch
    0.11
    inue
    0.10
    ingly
    0.09
    INUE
    0.09
    ers
    0.09
    ancy
    0.09
    ably
    0.08
    edly
    0.08
    ings
    0.08
    Activations Density 0.044%

    No Known Activations