© 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. 50264
    Prev
    Next
    INDEX
    Explanations

    programming keywords and commands

    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
    å¿ħçŃĶ
    -0.07
    ati
    -0.06
    ç«ĻåĨħæIJľç´¢
    -0.06
    天ç±ģ
    -0.06
    ii
    -0.06
    âĢIJ
    -0.06
    ·
    -0.06
    å¦Ĥæŀľä¸Ģ个
    -0.06
    ç¼Ķ
    -0.05
     Uploaded
    -0.05
    POSITIVE LOGITS
    gangs
    0.09
    ubb
    0.08
    rlen
    0.08
    áb
    0.08
    éli
    0.08
     Prepare
    0.08
    å¤ĸæĮĤ
    0.08
    chow
    0.07
    ovit
    0.07
    rop
    0.07
    Activations Density 0.045%

    No Known Activations