© 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. 51200
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and division

    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
    åIJ«ç¬ij
    -0.09
    éļı
    -0.08
    achs
    -0.08
    LEX
    -0.07
    é²²
    -0.07
    ahah
    -0.07
    ä¸ĢæŦåĩºçİ°
    -0.07
    lator
    -0.06
    å±±ä¸ĭ
    -0.06
    ä¸ĢéĢļ
    -0.06
    POSITIVE LOGITS
    æ¼¾
    0.07
    Convert
    0.07
    ugian
    0.07
     victim
    0.07
    æ¿Ł
    0.06
    converted
    0.06
     tém
    0.06
    åĬŁ
    0.06
    ä¹ĭéķ¿
    0.06
    窩
    0.06
    Activations Density 0.006%

    No Known Activations