© 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. 23753
    Prev
    Next
    INDEX
    Explanations

    direct current

    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
    _SUS
    -0.07
    çĸı
    -0.07
    asper
    -0.07
    Öĩ
    -0.07
    çŃĭ骨
    -0.06
    olim
    -0.06
    oeff
    -0.06
    寡
    -0.06
    åĬŁ
    -0.06
    æ°´åľŁ
    -0.06
    POSITIVE LOGITS
    转为
    0.08
    urnal
    0.07
    dbh
    0.07
    æłĹ
    0.07
    vip
    0.07
    ifar
    0.07
    uchen
    0.07
     tzw
    0.07
    äºĭäºĭ
    0.07
    aker
    0.07
    Activations Density 0.682%

    No Known Activations