© 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. 30836
    Prev
    Next
    INDEX
    Explanations

    prussides, sulfate, alginate, carbamate

    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
    çĩĥ
    -0.08
    èħ¹åľ°
    -0.06
    comments
    -0.06
    ython
    -0.06
    竹åŃIJ
    -0.06
    åį§åºĬ
    -0.06
    çĭ¼
    -0.06
    ç¬Ļ
    -0.06
     Roth
    -0.06
     lá»Ńa
    -0.06
    POSITIVE LOGITS
    ÒĽÑĭ
    0.08
    antiago
    0.08
    ан
    0.08
    à¹īา
    0.08
    姥
    0.07
    ä½łä¸įçŁ¥éģĵ
    0.07
    uchar
    0.07
    cker
    0.07
    undy
    0.07
    å»ĵ
    0.07
    Activations Density 0.001%

    No Known Activations