© 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. 49887
    Prev
    Next
    INDEX
    Explanations

    lists or catalogs of items

    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
     stake
    -0.08
    cesa
    -0.08
     Stake
    -0.07
    ä¸īéĥ¨æĽ²
    -0.07
    ä¸ī个éĺ¶æ®µ
    -0.07
    rito
    -0.07
    _parms
    -0.07
    маÑĤо
    -0.07
    prime
    -0.07
    åīįè¿Ľ
    -0.07
    POSITIVE LOGITS
     catalog
    0.13
    åĪĹ表
    0.13
     list
    0.13
     catalogue
    0.13
    åIJįå½ķ
    0.12
    listed
    0.12
    catalog
    0.12
    æ¸ħåįķ
    0.11
    list
    0.11
     listed
    0.11
    Activations Density 0.955%

    No Known Activations