© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    depends on

    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
    ä¸įåı¯æĢķ
    -0.07
    rauch
    -0.07
    çļĦ主æµģ
    -0.07
    çĦ¶å¤§
    -0.07
     Legislat
    -0.07
    åIJĵ人
    -0.07
     contado
    -0.07
     voet
    -0.07
    主æµģ
    -0.07
    γγ
    -0.07
    POSITIVE LOGITS
     depending
    0.09
    Depending
    0.09
     Depending
    0.09
     tuỳ
    0.08
    åıĸåĨ³äºİ
    0.07
    depending
    0.07
    isar
    0.07
    çĶ¨ä»¥
    0.07
     Ñģеле
    0.07
    oba
    0.07
    Activations Density 0.023%

    No Known Activations