© 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. 29414
    Prev
    Next
    INDEX
    Explanations

    assignment operators

    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
     vess
    -0.08
    esel
    -0.08
    seau
    -0.08
    öks
    -0.07
    dcc
    -0.07
    _BREAK
    -0.07
    rig
    -0.07
    æľĽåIJij
    -0.07
    ä»İ严
    -0.07
    mund
    -0.07
    POSITIVE LOGITS
    象
    0.07
    ç®Ģ
    0.07
    ç»ıæµİåĴĮ
    0.06
    ehu
    0.06
    è¯Ŀ
    0.06
    çĥŁ
    0.06
    éģĵ
    0.06
    æ¡ij
    0.06
    amps
    0.06
    ç½®
    0.06
    Activations Density 0.004%

    No Known Activations