© 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. 45315
    Prev
    Next
    INDEX
    Explanations

    people and relationships

    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
    ysi
    -0.07
    åºı
    -0.07
    entai
    -0.07
    éĢ®
    -0.07
    nid
    -0.07
    ä½łåĴĮ
    -0.07
    åħ¨ä½ĵæĪIJåijĺ
    -0.06
    lass
    -0.06
    æĥ³æĸ¹
    -0.06
    éĻIJåĶ®
    -0.06
    POSITIVE LOGITS
     whom
    0.10
    _named
    0.07
     unrelated
    0.07
     chosen
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    oulos
    0.07
    chosen
    0.07
     namens
    0.07
    åIJįåı«
    0.07
    -selected
    0.07
    Activations Density 0.348%

    No Known Activations