© 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. 8206
    Prev
    Next
    INDEX
    Explanations

    actor names in movie plots

    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
    _draft
    -0.08
    वल
    -0.07
    å²ģçĶŁæĹ¥
    -0.07
    umul
    -0.07
     bye
    -0.07
    å¼łæĻĵ
    -0.06
    åĪ«èĩ´
    -0.06
    åij¼
    -0.06
    çŀİ
    -0.06
    -media
    -0.06
    POSITIVE LOGITS
    饰æ¼ĶçļĦ
    0.12
    饰æ¼Ķ
    0.11
    æ¼Ķç»İ
    0.10
     actor
    0.10
    åĩºæ¼Ķ
    0.10
     portraying
    0.09
    飾æ¼Ķ
    0.09
    è¯łéĩĬ
    0.09
     interpreta
    0.09
    è©®éĩĭ
    0.08
    Activations Density 0.342%

    No Known Activations