© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62712
    Prev
    Next
    INDEX
    Explanations

    statistical tests and analysis

    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
    linky
    -0.10
    eworld
    -0.08
    phinx
    -0.08
    ç¼¥
    -0.07
    Ľ°
    -0.07
    etil
    -0.07
    çİĦå¹»å°ı说
    -0.07
    erland
    -0.07
    -prepend
    -0.07
     leg
    -0.07
    POSITIVE LOGITS
     conducted
    0.08
    éĢĤçĶ¨äºİ
    0.08
     appropriate
    0.07
     generalized
    0.07
     INDIRECT
    0.07
     assessing
    0.07
    aglia
    0.07
     covariance
    0.07
    建åįİ
    0.07
    appropriate
    0.07
    Activations Density 0.017%

    No Known Activations