© 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. 60938
    Prev
    Next
    INDEX
    Explanations

    storing data

    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
    å°½æľī
    -0.09
    uruh
    -0.08
     rút
    -0.08
    kaÅĦ
    -0.07
    .dsl
    -0.07
     ź
    -0.07
    opter
    -0.07
     unexpectedly
    -0.07
    .cmd
    -0.07
    _charset
    -0.07
    POSITIVE LOGITS
     storing
    0.13
     ÑħÑĢаниÑĤÑĮ
    0.10
     stored
    0.10
    åŃĺæĶ¾
    0.10
     ÑħÑĢан
    0.10
     stores
    0.09
    åŃĺåĤ¨
    0.09
    åı¯ä»¥éļıæŶ
    0.09
     Stores
    0.09
     ÑħÑĢанение
    0.09
    Activations Density 0.110%

    No Known Activations