© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30087
    Prev
    Next
    INDEX
    Explanations

    also, first, or really

    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
    ä½Ĩè¿Ļç§į
    -0.08
    ä½Ĩ并ä¸į
    -0.08
    ä½Ĩ缮åīį
    -0.07
    ä½Ĩä»ĸçļĦ
    -0.07
    enges
    -0.07
    ä½ĨæĦ¿
    -0.07
    èĻ½çĦ¶
    -0.07
    åĽłèĢĮ
    -0.07
    ä½Ĩä¸į
    -0.07
    ä½Ĩæľª
    -0.07
    POSITIVE LOGITS
     importantly
    0.09
    anan
    0.08
    ä¸İæѤåIJĮæŶ
    0.07
    anen
    0.07
    anol
    0.07
    —the
    0.07
    è¿Ļæł·ä¸Ģç§į
    0.07
    éĹ®é¢ĺæĿ¥äºĨ
    0.07
    ú
    0.07
    iamo
    0.07
    Activations Density 0.071%

    No Known Activations