© 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. 46845
    Prev
    Next
    INDEX
    Explanations

    contract related terms

    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
    -0.09
    ffect
    -0.07
     Äijặn
    -0.07
    wards
    -0.06
    irm
    -0.06
    éļĪ
    -0.06
    تÙħاÙħ
    -0.06
    sembl
    -0.06
     constantemente
    -0.06
    andar
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĽŀäºĭ
    0.10
    ypes
    0.10
     chẽ
    0.10
    ulary
    0.09
    ual
    0.09
    ually
    0.09
    sWith
    0.09
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.09
    .ua
    0.09
    ype
    0.09
    Activations Density 0.032%

    No Known Activations