© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24031
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons and questions

    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
    owell
    -0.07
    妥
    -0.07
    ieber
    -0.06
    oth
    -0.06
    erti
    -0.06
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.06
     Cruc
    -0.06
    вед
    -0.06
    æīįæĺ¯æľĢ
    -0.06
    zent
    -0.06
    POSITIVE LOGITS
     **.**
    0.08
     **:**
    0.07
    à¸Ńà¸ĩ
    0.07
    >>>>>>>
    0.07
    ,__
    0.07
    ErrorException
    0.07
    çĨł
    0.07
    miar
    0.07
    icorn
    0.07
     (*((
    0.07
    Activations Density 0.021%

    No Known Activations