© 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. 40848
    Prev
    Next
    INDEX
    Explanations

    home and family

    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
    ìļķ
    -0.08
    ked
    -0.07
    bsd
    -0.07
    èĥĥåı£
    -0.07
    ded
    -0.07
    isine
    -0.07
    erus
    -0.06
    schlag
    -0.06
    æĢģ度
    -0.06
    orthy
    -0.06
    POSITIVE LOGITS
    åİŁæĿ¥çļĦ
    0.11
    åİŁæľī
    0.10
    çĨŁæĤīçļĦ
    0.09
     пÑĢивÑĭ
    0.09
     cũ
    0.09
    æŧ
    0.09
    åİŁæľīçļĦ
    0.08
    à¹Ģà¸Ķิม
    0.08
     familiar
    0.08
    念念ä¸įå¿ĺ
    0.08
    Activations Density 0.197%

    No Known Activations