© 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. 17227
    Prev
    Next
    INDEX
    Explanations

    NBH, benfluorex, atorvastatin, verapamil

    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
    )|
    -0.07
    é¦
    -0.06
    wo
    -0.06
    éģIJ
    -0.06
    åħį
    -0.06
    èī¯
    -0.06
    ç®Ĺä¸įä¸Ĭ
    -0.06
    ti
    -0.06
     "
    -0.06
    //{{
    -0.06
    POSITIVE LOGITS
    æ¯Ķä¾ĭ为
    0.13
    éĢĤéĩı
    0.13
    è§Ħ模为
    0.13
    éĢĤéĩıçļĦ
    0.12
    æĮīæ¯Ķä¾ĭ
    0.12
     scaled
    0.11
    ä¸Ģå®ļéĩıçļĦ
    0.11
    æ¯Ķä¾ĭ
    0.10
    å®ļéĩı
    0.10
     proportional
    0.10
    Activations Density 0.549%

    No Known Activations