© 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. 43527
    Prev
    Next
    INDEX
    Explanations

    number sequences and cases

    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
    ิà¸ģสà¹Į
    -0.08
    erson
    -0.07
    à§įথ
    -0.07
    ellone
    -0.07
    ora
    -0.07
    Ñĩай
    -0.07
    fare
    -0.07
    ness
    -0.07
    orable
    -0.06
    oz
    -0.06
    POSITIVE LOGITS
    <tool_response>
    0.09
    æĸ¹èĪŁ
    0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.08
    ght
    0.08
    ramid
    0.08
    лез
    0.08
    ạn
    0.08
    oped
    0.08
    æĪIJç«ł
    0.08
    mented
    0.08
    Activations Density 0.266%

    No Known Activations