© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16879
    Prev
    Next
    INDEX
    Explanations

    cell, pair, user, node, finger, row, layer, station

    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
    èĥľ
    -0.07
    éĿ
    -0.06
    ä¸Ģç½ij
    -0.06
    Ãło
    -0.06
    çĿ¦
    -0.06
    -0.06
    Named
    -0.06
    orex
    -0.06
    ined
    -0.06
    触
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.09
    ìĬ¨
    0.08
    è¦ģä¹Ī
    0.08
    ajara
    0.08
     wise
    0.07
    éĥ½æľīä¸Ģ
    0.07
    wise
    0.07
    owitz
    0.07
    æł¹æį®èĩªèº«
    0.07
    ampp
    0.07
    Activations Density 0.030%

    No Known Activations