© 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. 46064
    Prev
    Next
    INDEX
    Explanations

    defining or describing phrases

    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
    ick
    -0.08
    cks
    -0.07
    icked
    -0.07
    varez
    -0.07
    ags
    -0.07
    æľĢåħĪ
    -0.07
    ck
    -0.06
    opolitan
    -0.06
    ä¿Ŀè¯ģäºĨ
    -0.06
    orts
    -0.06
    POSITIVE LOGITS
    ãi
    0.07
    acus
    0.07
    ä»ĭéĿ¢
    0.07
    asn
    0.07
    è°Ĭ
    0.06
    lair
    0.06
    pond
    0.06
    iom
    0.06
    æ²ŁæĿij
    0.06
    HT
    0.06
    Activations Density 0.008%

    No Known Activations