© 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. 23638
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĥij
    -0.06
    ukum
    -0.06
    ikh
    -0.06
    æĥŃ
    -0.06
    çĶŁæĹ¥å¿«ä¹IJ
    -0.06
    转
    -0.06
    åŃŁ
    -0.06
    éĺ´
    -0.06
    è¾½
    -0.06
    å¼Ĥ
    -0.06
    POSITIVE LOGITS
    .xhtml
    0.08
    schild
    0.07
    atform
    0.07
    øren
    0.07
     Wyst
    0.07
    angling
    0.07
    -uri
    0.07
    ï¸İ
    0.07
    _PLACE
    0.07
    odings
    0.07
    Activations Density 0.000%

    No Known Activations