© 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. 20596
    Prev
    Next
    INDEX
    Explanations

    pig skeletal

    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
    mente
    -0.09
    à§įত
    -0.08
    ujuan
    -0.08
    ucho
    -0.08
    ê³±
    -0.07
    rát
    -0.07
    zza
    -0.07
    æ®Ĩå°½
    -0.07
    -esque
    -0.07
    æĥħåĨµåIJİ
    -0.07
    POSITIVE LOGITS
    à¹Ĩ
    0.13
    ãĢħãģ®
    0.12
     à¹Ĩ
    0.12
    éĥ¨å°±
    0.10
    ìį¨
    0.10
    ãĢħ
    0.09
    交æīĢ
    0.09
    ovima
    0.09
    åŃIJçļĦ
    0.09
    åĦ¿çļĦ
    0.09
    Activations Density 0.011%

    No Known Activations