© 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. 60751
    Prev
    Next
    INDEX
    Explanations

    BufferedReader instantiation

    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
    itag
    -0.08
    rosse
    -0.08
    ianos
    -0.08
    hots
    -0.07
    ube
    -0.07
    å®ĪåĪĻ
    -0.07
    imientos
    -0.07
    ub
    -0.07
    ball
    -0.07
    æĸ¹èĥ½
    -0.07
    POSITIVE LOGITS
    ¿
    0.07
    /rfc
    0.07
    ÛĮÙģ
    0.07
    åij¼
    0.07
    æĺŃ
    0.07
    ussa
    0.07
    faz
    0.07
    éĢ¸
    0.06
    /oauth
    0.06
    åįĩèµ·
    0.06
    Activations Density 0.001%

    No Known Activations