© 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. 58433
    Prev
    Next
    INDEX
    Explanations

    preliminary investigation

    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
    <|box_end|>
    -0.10
    å°Ķå¤ļ
    -0.09
    纷åijĪ
    -0.09
    strand
    -0.09
    ulich
    -0.09
    argo
    -0.09
    less
    -0.09
    ancis
    -0.09
    亲æľĭ
    -0.09
    ़
    -0.09
    POSITIVE LOGITS
    ly
    0.09
    åĴĮ
    0.09
    (
    0.08
    ynet
    0.08
    èĩªå·±
    0.06
    -
    0.06
     set
    0.06
    áºŃu
    0.06
    ity
    0.06
    ↵↵
    0.06
    Activations Density 0.003%

    No Known Activations