© 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. 61389
    Prev
    Next
    INDEX
    Explanations

    PI3K/Akt signaling pathway

    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
    opped
    -0.07
    axed
    -0.07
    _COLL
    -0.07
     datum
    -0.07
    à¸Ĭิà¹īà¸Ļ
    -0.07
    pra
    -0.07
    forder
    -0.06
    æł·æľ¬
    -0.06
    stdin
    -0.06
    èĽŁ
    -0.06
    POSITIVE LOGITS
     pathways
    0.11
     pathway
    0.10
    -mediated
    0.10
    éĢļè·¯
    0.09
    éĢĶå¾Ħ
    0.09
     activation
    0.08
    medi
    0.08
    ä¸Ńè·¯
    0.08
    ç³»çļĦ
    0.08
    endorf
    0.08
    Activations Density 0.245%

    No Known Activations