© 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. 64987
    Prev
    Next
    INDEX
    Explanations

    VPN, OPT, Widget, services, hosting

    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
     Enth
    -0.06
     som
    -0.06
    æĬĬæīĢæľīçļĦ
    -0.06
    为建设
    -0.06
    对æĸ°
    -0.06
     aver
    -0.06
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ķัว
    -0.06
    çľĭä¸į
    -0.06
    ëłĪìĬ¤
    -0.06
     POUR
    -0.06
    POSITIVE LOGITS
    джа
    0.08
    ipse
    0.08
    vail
    0.08
    /embed
    0.08
    asia
    0.08
    adin
    0.08
    ầm
    0.08
     carve
    0.07
    åŃĹè¯į
    0.07
    å®Įç¾İä¸ĸçķĮ
    0.07
    Activations Density 0.035%

    No Known Activations