© 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. 42300
    Prev
    Next
    INDEX
    Explanations

    movement and flow

    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
     dessus
    -0.08
    bjerg
    -0.08
    æĬĬä¸Ģ个
    -0.07
    ortable
    -0.07
    åѦçĶŁå¯¹
    -0.07
    _listing
    -0.07
    对åѦçĶŁ
    -0.07
    elog
    -0.07
    大家对
    -0.07
    æīįèĥ½è®©
    -0.07
    POSITIVE LOGITS
    ä¸įè¿ľ
    0.08
     passes
    0.08
    并ç»ı
    0.08
     eventual
    0.07
    并æľĢç»Ī
    0.07
     pass
    0.07
     passing
    0.07
    æľªè¢«
    0.07
     onward
    0.07
    å°ijéĥ¨åĪĨ
    0.07
    Activations Density 0.066%

    No Known Activations