© 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. 18474
    Prev
    Next
    INDEX
    Explanations

    foo

    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
    RB
    -0.07
     {?}
    -0.07
    饶
    -0.07
    å¾ĺå¾Ĭ
    -0.07
     below
    -0.06
    Amb
    -0.06
     dessous
    -0.06
    AMB
    -0.06
    RH
    -0.06
    otto
    -0.06
    POSITIVE LOGITS
    ä»ħæѤ
    0.08
    继ç»Ń沿
    0.08
     Alber
    0.08
    wed
    0.08
    wand
    0.07
     apologise
    0.07
    rani
    0.07
    èįīæľ¨
    0.07
    æµĨ
    0.07
    å¾·æĭī
    0.07
    Activations Density 0.004%

    No Known Activations