© 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. 48929
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
    æĸĩåĮĸçŁ¥è¯Ĩ
    -0.07
    quel
    -0.07
    访
    -0.07
    æĹłæ³ķ满足
    -0.07
    chw
    -0.06
    gni
    -0.06
    äste
    -0.06
    .chunk
    -0.06
    ÐŁÐļ
    -0.06
    计ç®Ĺåĩº
    -0.06
    POSITIVE LOGITS
    æĹłè¸ª
    0.07
     cÃŃ
    0.07
    ç»ĻåĩºçļĦ
    0.07
    orgia
    0.07
    è´°
    0.07
    jon
    0.07
    为æѤ
    0.07
     broadly
    0.07
    åħ·ä½ĵè¦ģæ±Ĥ
    0.07
     Dafür
    0.06
    Activations Density 0.033%

    No Known Activations