© 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. 52195
    Prev
    Next
    INDEX
    Explanations

    log reduction, prayer, license, patent

    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
    elen
    -0.08
    alom
    -0.07
    Unnamed
    -0.07
    borg
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    itera
    -0.07
    ôt
    -0.07
    еÑĢбÑĥ
    -0.07
    iness
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    POSITIVE LOGITS
    าศ
    0.07
    appa
    0.07
    Ø·
    0.07
    pData
    0.06
    窩
    0.06
     تعاÙĦÙī
    0.06
    /operators
    0.06
    örn
    0.06
    onda
    0.06
    vio
    0.06
    Activations Density 0.005%

    No Known Activations