© 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. 46469
    Prev
    Next
    INDEX
    Explanations

    in my

    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
    ymm
    -0.07
    å¸Ĥåľºä¸Ĭ
    -0.07
    usy
    -0.06
    éĤij
    -0.06
     запо
    -0.06
    以èĩªå·±
    -0.06
    van
    -0.06
    bao
    -0.06
    乳头
    -0.06
    åħĪè¡Į
    -0.06
    POSITIVE LOGITS
    ä¸Ģå¤Ħ
    0.09
     somewhere
    0.08
    åĵªåĦ¿
    0.08
    两å¤Ħ
    0.08
    åĵªéĩĮ
    0.08
     section
    0.08
    å±ħæĺĵ
    0.08
    æĺ¾çľ¼
    0.08
    ä½ķå¤Ħ
    0.08
     lähellä
    0.07
    Activations Density 0.407%

    No Known Activations