© 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. 10945
    Prev
    Next
    INDEX
    Explanations

    brazzers

    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
     âĢ¦
    -0.07
     ‘
    -0.06
     hal
    -0.06
    åıªå¾Ĺ
    -0.06
    æĥ³åĥı
    -0.06
    ‘
    -0.06
    anto
    -0.06
    est
    -0.06
     tini
    -0.06
    è¯ļ
    -0.06
    POSITIVE LOGITS
    èĭ¦å¿ĥ
    0.09
    rasz
    0.08
    alts
    0.08
    roh
    0.08
    ä½Ľç¥ĸ
    0.08
    èŃľ
    0.08
     Dern
    0.08
    ẫ
    0.08
    iol
    0.08
    alang
    0.08
    Activations Density 0.005%

    No Known Activations