© 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. 49303
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and greek letters

    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
    çķij
    -0.06
    åŦ
    -0.06
     stray
    -0.06
    ç¿Ĵ
    -0.06
    åī§
    -0.06
    èĸĦ
    -0.06
    iegend
    -0.06
    梦å¯IJ以æ±Ĥ
    -0.06
    gee
    -0.06
    åĬĩ
    -0.06
    POSITIVE LOGITS
    è¶Ĭèµ°è¶Ĭ
    0.08
    æį®è¯´
    0.07
    tores
    0.07
    éĹŃ
    0.07
    åľ¨å¤§
    0.07
    ois
    0.07
     Ñģеле
    0.07
    ilé
    0.07
    eken
    0.07
    ienza
    0.07
    Activations Density 0.046%

    No Known Activations