© 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. 18643
    Prev
    Next
    INDEX
    Explanations

    _type or content_type

    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
    yun
    -0.08
    bers
    -0.07
    éģĹ
    -0.06
    ê¼
    -0.06
     mú
    -0.06
    ices
    -0.06
     Tal
    -0.06
    ä¸ĭ载使çĶ¨
    -0.06
    Sortable
    -0.06
     tém
    -0.06
    POSITIVE LOGITS
     type
    0.10
    type
    0.09
    -type
    0.09
    ç±»åŀĭ
    0.09
    _type
    0.09
    Type
    0.09
     CommandType
    0.09
     Type
    0.09
    (type
    0.08
     setType
    0.08
    Activations Density 0.251%

    No Known Activations