© 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. 57502
    Prev
    Next
    INDEX
    Explanations

    triplet loss generation

    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
    rapy
    -0.09
    ÑĪава
    -0.08
    ¤íĹ
    -0.08
     Höh
    -0.08
    ÑĤеа
    -0.07
    )(((
    -0.07
    acman
    -0.07
    为å®ĺ
    -0.07
    issant
    -0.07
    .Mode
    -0.07
    POSITIVE LOGITS
    en
    0.07
    æ¥ł
    0.06
    ï¾ŀ
    0.06
    éĩij森
    0.06
    å°Ķ夫
    0.06
    绪
    0.06
    æĥĬå¿ĥåĬ¨
    0.06
    éĿĻçļĦ
    0.06
    ol
    0.06
    am
    0.06
    Activations Density 0.211%

    No Known Activations