© 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. 49692
    Prev
    Next
    INDEX
    Explanations

    modified or updated versions

    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
    uera
    -0.07
    .ov
    -0.07
    åľ¨æīĢ
    -0.07
    bose
    -0.07
    ekre
    -0.06
    <typeof
    -0.06
    umah
    -0.06
    åħ±åIJĮ为
    -0.06
    за
    -0.06
     whence
    -0.06
    POSITIVE LOGITS
     revised
    0.08
     modified
    0.07
     Revised
    0.07
     redesigned
    0.07
     revis
    0.07
    _Default
    0.07
    ieu
    0.07
     poorly
    0.07
     Updated
    0.07
     UPDATED
    0.07
    Activations Density 0.432%

    No Known Activations