© 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. 29710
    Prev
    Next
    INDEX
    Explanations

    fulfillment and compliance

    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
    ically
    -0.10
    -0.08
    æł·çļĦ
    -0.08
     lá»Ńa
    -0.08
    IALOG
    -0.08
    reme
    -0.07
    sembler
    -0.07
    ownt
    -0.07
    elsey
    -0.07
    inale
    -0.07
    POSITIVE LOGITS
    åħµå½¹
    0.08
     obligations
    0.08
    ä¸įäºĨ
    0.08
    ä¸įäºĨçļĦ
    0.08
    ances
    0.08
    ÑĤон
    0.08
    iendo
    0.08
    ERIC
    0.08
    fills
    0.07
    ancing
    0.07
    Activations Density 0.020%

    No Known Activations