© 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. 32871
    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
    ample
    -0.07
    reiro
    -0.07
    ure
    -0.07
     conveniently
    -0.07
    _REFER
    -0.07
    太çĻ½
    -0.06
    山海
    -0.06
    ries
    -0.06
    uras
    -0.06
    çļĦç¡®
    -0.06
    POSITIVE LOGITS
    åħ¶ä¹IJ
    0.07
    sville
    0.07
     dulu
    0.07
    ä¸īåĮħ
    0.07
    timing
    0.07
    schuss
    0.06
    skie
    0.06
    alj
    0.06
    :
    0.06
     publicity
    0.06
    Activations Density 0.000%

    No Known Activations