© 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. 44722
    Prev
    Next
    INDEX
    Explanations

    mathematical variables (d, h, r)

    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
    azzo
    -0.08
    ä¸Ģ课
    -0.08
    åİĨéĻ©
    -0.07
    azing
    -0.07
    Ú¯ÙĪÛĮ
    -0.07
    ifton
    -0.07
    igu
    -0.07
    ookie
    -0.07
    åķĨä¸ļçĶ¨éĢĶ
    -0.07
    gli
    -0.07
    POSITIVE LOGITS
    erais
    0.07
    vc
    0.06
    æľĭ
    0.06
    hek
    0.06
    çĹĽ
    0.06
     Pah
    0.06
    à¸ķั
    0.06
    øj
    0.06
    uais
    0.06
    ç¿ģ
    0.06
    Activations Density 0.185%

    No Known Activations