© 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. 2583
    Prev
    Next
    INDEX
    Explanations

    year, filed

    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
    太éĥİ
    -0.08
    gett
    -0.07
     Fanpage
    -0.07
    imits
    -0.07
    enery
    -0.07
    anium
    -0.07
    ingu
    -0.07
    seh
    -0.07
    thouse
    -0.07
    ingly
    -0.06
    POSITIVE LOGITS
    åħ®
    0.07
    俱ä¹IJéĥ¨
    0.07
    à¹ģà¸Ļว
    0.07
    åľ°å¼Ģå±ķ
    0.06
    çĪµ
    0.06
    rd
    0.06
    ç§ijæĬĢåıijå±ķ
    0.06
    ÑĪев
    0.06
    robi
    0.06
    èģĮä¸ļæĬĢæľ¯åѦéĻ¢
    0.06
    Activations Density 0.365%

    No Known Activations