© 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. 26571
    Prev
    Next
    INDEX
    Explanations

    cultural geography and influences

    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
    ients
    -0.07
    éĻ¤æģ¶
    -0.07
    åħ¨éĺŁ
    -0.07
     undisclosed
    -0.07
    å¸ĮæľĽä½łèĥ½
    -0.06
    arnings
    -0.06
     photoc
    -0.06
     fid
    -0.06
    udit
    -0.06
    css
    -0.06
    POSITIVE LOGITS
    èŀįåIJĪ
    0.11
    èŀįåIJĪåıijå±ķ
    0.11
     influences
    0.11
     thriving
    0.10
     influence
    0.10
    åŃķèĤ²
    0.10
     flourishing
    0.10
    ä¼łåħ¥
    0.09
    èŀįåIJĪçļĦ
    0.09
     nurt
    0.09
    Activations Density 0.154%

    No Known Activations