© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    drug design and screening

    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
    ilag
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.07
    aspers
    -0.07
    å±ħ
    -0.07
    illah
    -0.07
    è¡¡
    -0.06
     involuntary
    -0.06
    ì·¨
    -0.06
    ä¸Ģ缴ä¿ĿæĮģ
    -0.06
     pér
    -0.06
    POSITIVE LOGITS
     optimization
    0.09
     iter
    0.09
     experimentation
    0.09
    é¢Ħæµĭ
    0.09
    iter
    0.09
    Iter
    0.09
    è¿Ń代
    0.08
    çŃĽéĢī
    0.08
     iterative
    0.08
     Iter
    0.08
    Activations Density 0.098%

    No Known Activations