© 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. 43937
    Prev
    Next
    INDEX
    Explanations

    starting sequence

    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
    仲
    -0.07
     joined
    -0.07
    æĶ¶éĽĨæķ´çIJĨ
    -0.07
     bé
    -0.06
     conf
    -0.06
    cat
    -0.06
    INU
    -0.06
    amd
    -0.06
    ancellation
    -0.06
     conver
    -0.06
    POSITIVE LOGITS
    填满
    0.11
    ä¼ĺåħĪ
    0.11
    -fill
    0.11
    ä¸į足çļĦ
    0.10
    ä¾Ŀ次
    0.10
    åī©ä½ĻçļĦ
    0.10
    å°½åı¯èĥ½çļĦ
    0.10
     Æ°u
    0.10
    å°½åı¯èĥ½
    0.09
    æħ·
    0.09
    Activations Density 0.004%

    No Known Activations