© 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. 23695
    Prev
    Next
    INDEX
    Explanations

    cell cycle phase

    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
    สัà¸Ļ
    -0.07
    obel
    -0.06
    odable
    -0.06
    çİĩåľ¨
    -0.06
    éĻ¶
    -0.06
    heid
    -0.06
    åĴĮçĶ°
    -0.06
    åij¨å²ģ以ä¸Ĭ
    -0.06
    å¦Ĥçİī
    -0.06
    ध
    -0.06
    POSITIVE LOGITS
     stage
    0.07
     onwards
    0.07
    ricks
    0.07
    à¹Ģห
    0.07
    æł¸
    0.07
    distributed
    0.07
     phase
    0.07
    éĺ¶æ®µ
    0.07
     nuclear
    0.07
    ENOMEM
    0.07
    Activations Density 0.009%

    No Known Activations