© 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. 33839
    Prev
    Next
    INDEX
    Explanations

    omega chloroalkyld, insert commands every

    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
    lach
    -0.08
    åĭī
    -0.08
     Earn
    -0.08
     VS
    -0.07
    æĬ½
    -0.07
    VS
    -0.07
    ünd
    -0.07
    à¹Īาà¸Ļ
    -0.07
    еÑĩ
    -0.07
    VEST
    -0.07
    POSITIVE LOGITS
    éĥĬ
    0.08
    ENU
    0.07
    åıĭ好çļĦ
    0.07
    åļı
    0.06
    (dm
    0.06
    妮
    0.06
    axter
    0.06
    áĥ¯
    0.06
    UNUSED
    0.06
    çŀ§çŀ§
    0.06
    Activations Density 0.016%

    No Known Activations