© 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. 14099
    Prev
    Next
    INDEX
    Explanations

    typically, naturally, usually, always

    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
    èĬ¸
    -0.07
    ENU
    -0.07
    çļĦ羣æŃ£
    -0.07
    uhu
    -0.07
    _MACRO
    -0.07
    è¦ģéĢīæĭ©
    -0.07
     principally
    -0.07
    羣æŃ£çļĦ
    -0.07
     Signore
    -0.07
    æ§IJ
    -0.07
    POSITIVE LOGITS
    åĩ¡äºĭ
    0.11
     characteristic
    0.11
    åIJijæĿ¥
    0.10
    always
    0.09
     always
    0.09
    Always
    0.09
    èijĹ称
    0.09
     Always
    0.09
    ä¸ĢåIJij
    0.08
    åģļäºĭæĥħ
    0.08
    Activations Density 0.456%

    No Known Activations