© 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. 21459
    Prev
    Next
    INDEX
    Explanations

    (c) or copyright authors

    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
    antina
    -0.10
     **.**
    -0.10
    SharedPtr
    -0.09
    éĺħè¯»æľ¬æĸĩåīį
    -0.09
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.09
    undur
    -0.08
    é«ĺéĢŁä¸ĭè½½
    -0.08
    çijŀæĭī
    -0.08
    못
    -0.08
    liament
    -0.08
    POSITIVE LOGITS
     &
    0.06
     contributors
    0.06
    th
    0.06
    sty
    0.06
    0.06
     `
    0.06
     thanks
    0.06
     J
    0.06
     atom
    0.05
     Atom
    0.05
    Activations Density 0.337%

    No Known Activations