© 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. 63491
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns

    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
    umbo
    -0.06
     |âĢ¢
    -0.06
    ¯
    -0.06
    andler
    -0.06
     metam
    -0.06
     differentiate
    -0.06
     |
    -0.06
    å¸Ĥåľºè°ĥçłĶ
    -0.06
     Foley
    -0.06
    alay
    -0.06
    POSITIVE LOGITS
    æľĢç»ĪçļĦ
    0.10
    æľĢç»Ī
    0.09
    ç»ĵæŀľæĺ¯
    0.09
     concluding
    0.08
     outputs
    0.08
     finishing
    0.08
    çļĦæľĢç»Ī
    0.08
    final
    0.08
     final
    0.08
    å®ĮæĪIJçļĦ
    0.08
    Activations Density 0.020%

    No Known Activations