© 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. 16863
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     pari
    -0.07
    à¸ģุล
    -0.07
    娥
    -0.07
    äºķçĦ¶
    -0.07
    ħ
    -0.06
     Goed
    -0.06
    åĽ¾èħ¾
    -0.06
    isht
    -0.06
    ButtonDown
    -0.06
    عÙĦÙĨت
    -0.06
    POSITIVE LOGITS
    äºijå³°
    0.08
    å¼¥
    0.07
    éĩĮ没æľī
    0.07
    å¤ĸç§ij
    0.07
    apg
    0.07
    失
    0.07
    åĬłçļĦ
    0.07
    aha
    0.07
    ritch
    0.06
    天å¤ĸ
    0.06
    Activations Density 0.151%

    No Known Activations