© 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. 41811
    Prev
    Next
    INDEX
    Explanations

    file paths and code elements

    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
    å¤ĸ
    -0.06
     Denn
    -0.06
    ACA
    -0.06
    agung
    -0.06
    zaam
    -0.06
    èĭ
    -0.06
    èĸª
    -0.06
    çļĦä¸Ģå¹ķ
    -0.06
    åĽºæľīçļĦ
    -0.06
    Hub
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ķà¹ĩà¸Ķ
    0.08
    _ADV
    0.08
    urul
    0.08
    éĺħè¯»æľ¬æĸĩ
    0.08
    å¾ij
    0.08
    äºĭä¸Ń
    0.07
    éĥ½åģļ
    0.07
    gur
    0.07
    amis
    0.07
    è¿Ļ项
    0.07
    Activations Density 0.035%

    No Known Activations