© 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. 41470
    Prev
    Next
    INDEX
    Explanations

    collect terms

    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
    omer
    -0.09
     chem
    -0.07
    umba
    -0.07
    åIJĮå¿Ĺ们
    -0.07
    anner
    -0.07
    lyn
    -0.07
    è¿Ļå°±éľĢè¦ģ
    -0.06
    erver
    -0.06
    ound
    -0.06
    chem
    -0.06
    POSITIVE LOGITS
    aime
    0.07
    olari
    0.07
     fav
    0.07
     concor
    0.07
    Destructor
    0.07
    avar
    0.06
    ıb
    0.06
    å°±ä¸Ĭ
    0.06
    olib
    0.06
     Yas
    0.06
    Activations Density 0.010%

    No Known Activations