© 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. 56233
    Prev
    Next
    INDEX
    Explanations

    ignores or overlooks

    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
    å°±æĺ¯äºĨ
    -0.08
    .Pull
    -0.07
    agas
    -0.07
    ä½ĨçĶ±äºİ
    -0.07
    æĺ¯ä½łçļĦ
    -0.07
    天å®ĩ
    -0.07
    isd
    -0.07
     effected
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    اث
    -0.07
    POSITIVE LOGITS
    忽çķ¥äºĨ
    0.15
    忽è§ĨäºĨ
    0.14
     overlook
    0.13
     ignores
    0.13
    忽çķ¥
    0.12
    忽è§Ĩ
    0.11
     overlooked
    0.11
     ignoring
    0.10
     ignored
    0.10
     ignore
    0.10
    Activations Density 0.141%

    No Known Activations