© 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. 33654
    Prev
    Next
    INDEX
    Explanations

    most common/frequent

    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
    ús
    -0.09
    klet
    -0.08
     additionally
    -0.08
     intentionally
    -0.07
    agio
    -0.07
    enville
    -0.07
    anyol
    -0.07
    .lv
    -0.07
    ÅĤasz
    -0.07
    ulon
    -0.07
    POSITIVE LOGITS
     logical
    0.09
    çIJĨ
    0.08
    稳妥
    0.08
    ä¹ĭåıĪ
    0.07
    .annotation
    0.07
     Logical
    0.07
     realistic
    0.07
    oux
    0.07
     пÑĢоÑĩ
    0.06
    æĥħçIJĨ
    0.06
    Activations Density 0.033%

    No Known Activations