© 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. 32189
    Prev
    Next
    INDEX
    Explanations

    tr-suffix words

    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
    inho
    -0.07
    ho
    -0.07
    еÑģÑģи
    -0.07
    è¿Łè¿Ł
    -0.07
    è¿ŀäºij
    -0.07
    åĴ³åĴ³
    -0.07
    æīĵäºĨ个
    -0.07
    åį´è¿ĺæĺ¯
    -0.07
    è¿Ļ个社ä¼ļ
    -0.07
    ãĤ¦ãĥī
    -0.07
    POSITIVE LOGITS
    rts
    0.08
    ÙĦØ©
    0.07
    ported
    0.06
    araf
    0.06
    çݲ
    0.06
    عاÙĨ
    0.06
    ellet
    0.06
    æ´¾åĩº
    0.06
    opil
    0.06
    -awesome
    0.06
    Activations Density 0.831%

    No Known Activations