© 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. 63141
    Prev
    Next
    INDEX
    Explanations

    column names

    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
    .autoconfigure
    -0.07
    üz
    -0.07
    ιÏİ
    -0.07
    çĶ¨å®Į
    -0.07
    åŁĭåľ¨
    -0.07
    åķĨæłĩä¿¡æģ¯
    -0.07
     subrange
    -0.06
    enal
    -0.06
    éģĩ
    -0.06
    dirs
    -0.06
    POSITIVE LOGITS
     column
    0.13
    æłı
    0.12
     columns
    0.12
    -column
    0.11
    column
    0.11
    æ¬Ħ
    0.11
     Column
    0.10
    æłı缮
    0.10
    .getColumn
    0.10
    åĪĹ
    0.10
    Activations Density 0.169%

    No Known Activations