© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    after ingestion or intravenous injection

    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
    å¾ħ人
    -0.08
     Ilmais
    -0.08
    赤水
    -0.07
    roc
    -0.07
     trái
    -0.07
    elij
    -0.07
    PN
    -0.07
     stok
    -0.07
    ptron
    -0.07
    ugier
    -0.07
    POSITIVE LOGITS
    æ´ŀ
    0.08
    å¿ł
    0.07
    æ¯Ķ以å¾Ģ
    0.07
    iring
    0.07
     Kaw
    0.07
    åij¢
    0.07
    æľīå½±åĵį
    0.06
    å½±åĵįåĪ°
    0.06
    åħ¶ä¸Ńæľī
    0.06
    äºĨä¸Ģç§į
    0.06
    Activations Density 0.187%

    No Known Activations