© 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. 2609
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    à¹īà¸Ń
    -0.07
    yte
    -0.07
    дли
    -0.07
    otel
    -0.06
    ìŁģ
    -0.06
    arana
    -0.06
    çĻ¾å¿Ļ
    -0.06
    Ĩµ
    -0.06
    allo
    -0.06
    heed
    -0.06
    POSITIVE LOGITS
    _ARR
    0.08
    auff
    0.07
    à¹ģà¸ģร
    0.07
    ouz
    0.07
    æĹłæĤĶ
    0.07
    訴
    0.07
    éĩĩè´Ńåįķä½į
    0.07
    宸
    0.07
    íĪ¬
    0.07
    説
    0.07
    Activations Density 0.000%

    No Known Activations