© 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. 30151
    Prev
    Next
    INDEX
    Explanations

    word endings or grammatical structures

    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
    urable
    -0.08
    èĩ³å°ijåľ¨
    -0.07
    èĶļ
    -0.07
    å°±æĺ¯äºĨ
    -0.07
    azzi
    -0.06
    æļĤæŶ
    -0.06
    å¯ĵæķĻäºİ
    -0.06
    -any
    -0.06
    \:
    -0.06
    èĩ³å°ij
    -0.06
    POSITIVE LOGITS
     padahal
    0.16
     instead
    0.14
    instead
    0.14
     Padahal
    0.14
     ÑıкобÑĭ
    0.13
    è¿ĩæĹ©
    0.11
     вмеÑģÑĤо
    0.11
     unnecessarily
    0.11
    èĢĮ没æľī
    0.11
    èĢĮä¸įæĺ¯
    0.11
    Activations Density 0.320%

    No Known Activations