© 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. 55880
    Prev
    Next
    INDEX
    Explanations

    scalar, Station, Vent, Schneider, Points

    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
    ikota
    -0.08
     McCart
    -0.07
    raš
    -0.07
    вок
    -0.07
    entai
    -0.07
    ateg
    -0.07
    Ðģ
    -0.07
    ึà¸ģ
    -0.07
    å¾·ç½Ĺ
    -0.07
    ere
    -0.07
    POSITIVE LOGITS
    æĿ¥èĩª
    0.10
    åĩºèĩª
    0.10
     part
    0.10
    å±ŀäºİ
    0.08
    éĢīèĩª
    0.08
     according
    0.08
     parte
    0.08
    à¹ĥà¸Ļระà¸ļà¸ļ
    0.08
    according
    0.08
    è§ģäºİ
    0.08
    Activations Density 1.879%

    No Known Activations