© 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. 20458
    Prev
    Next
    INDEX
    Explanations

    cytoplasm phosphorylation

    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
    eds
    -0.08
    edly
    -0.08
    ilah
    -0.07
    lap
    -0.07
    -uri
    -0.07
    court
    -0.07
     cad
    -0.07
    iten
    -0.07
    riles
    -0.06
    ings
    -0.06
    POSITIVE LOGITS
    æ·±å¤ĦçļĦ
    0.08
    inker
    0.08
    æ·±å¤Ħ
    0.08
    çĶŁäº§æĢ»åĢ¼
    0.08
    keletal
    0.08
    å¯ĦãģĽ
    0.08
    aneous
    0.08
    icha
    0.07
    éĩĮ约
    0.07
    Ò¡
    0.07
    Activations Density 0.030%

    No Known Activations