© 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. 10770
    Prev
    Next
    INDEX
    Explanations

    academic papers and scientific articles

    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
    ä¿Ŀ
    -0.07
    çķı
    -0.07
    æ´»
    -0.06
    anter
    -0.06
    éĢļ
    -0.06
    ç»ķ
    -0.06
    æĺĻ
    -0.06
    ao
    -0.06
    éĺ´
    -0.06
    ç¿»
    -0.06
    POSITIVE LOGITS
    essin
    0.09
    غاÙħ
    0.07
    æ¡ĥæĿİ
    0.07
    åĢ¼å¾Ĺä¹°
    0.07
    ัà¹īà¸ĩ
    0.07
    ITERAL
    0.07
    çĥŃæĴŃ
    0.07
    å©ļ纱çħ§
    0.07
    央è§Ĩæĸ°éĹ»
    0.07
     lesqu
    0.07
    Activations Density 0.042%

    No Known Activations