© 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. 16211
    Prev
    Next
    INDEX
    Explanations

    size, radius, diameter, type

    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
    heds
    -0.08
    èĢĥè¯ķåĨħ容
    -0.07
    اÙĦات
    -0.07
    ilas
    -0.07
    人å¿ĥçļĦ
    -0.07
    ä¹ĭæīĢ
    -0.06
    æ²īçĶ¸çĶ¸
    -0.06
    illion
    -0.06
    æŶéĹ´éĩĮ
    -0.06
    extras
    -0.06
    POSITIVE LOGITS
     whose
    0.09
     varying
    0.08
    åŀĭçļĦ
    0.08
     size
    0.07
    缮çļĦåľ¨äºİ
    0.07
     radius
    0.07
     type
    0.07
    èģĺ
    0.07
     equal
    0.07
     diameter
    0.07
    Activations Density 0.101%

    No Known Activations