© 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. 23374
    Prev
    Next
    INDEX
    Explanations

    covariant derivative

    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
    gren
    -0.08
    endu
    -0.07
    çŁ³åŃIJ
    -0.07
    anic
    -0.07
    ãģ«èĩ³
    -0.07
    çĻ¾åħ¬éĩĮ
    -0.07
     Parkway
    -0.07
    å¾Ģå¾Ģæĺ¯
    -0.07
    _verbose
    -0.07
    arcer
    -0.07
    POSITIVE LOGITS
    obe
    0.08
    身ãģ«
    0.07
    éļı
    0.07
    eda
    0.07
     برد
    0.07
    çķ´
    0.07
    fera
    0.07
    åĵģ
    0.06
    å¤ļæĥħ
    0.06
    ugh
    0.06
    Activations Density 0.002%

    No Known Activations