© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    the term paper

    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
    åıĪæĥ³
    -0.08
    ehr
    -0.08
    ozn
    -0.08
    agnes
    -0.08
    гÑĢÑĭ
    -0.08
    gmt
    -0.08
    angelog
    -0.07
    éĻ¤æѤ
    -0.07
    cesa
    -0.07
    ses
    -0.07
    POSITIVE LOGITS
    äºĨåĩłä¸ĭ
    0.06
    çłĶ究表æĺİ
    0.06
     undoubtedly
    0.06
    odore
    0.06
    stream
    0.06
    oner
    0.06
    ker
    0.06
    åIJ¬çĿĢ
    0.06
     trom
    0.06
     âĸª
    0.06
    Activations Density 0.063%

    No Known Activations