© 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. 17252
    Prev
    Next
    INDEX
    Explanations

    identity unknown

    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
    uger
    -0.08
    .gs
    -0.08
    rink
    -0.08
    ETHER
    -0.07
    toList
    -0.07
    λι
    -0.07
    åģ¥åº·åĴĮ
    -0.07
    ecen
    -0.07
    å¨ģé£İ
    -0.07
    ->__
    -0.07
    POSITIVE LOGITS
     unidentified
    0.16
     unnamed
    0.16
     anonymous
    0.16
     unknown
    0.15
    anonymous
    0.15
     unspecified
    0.14
    unknown
    0.14
    ä¸įæĺİ
    0.14
    Unknown
    0.14
    åĮ¿åIJį
    0.14
    Activations Density 0.491%

    No Known Activations