© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59800
    Prev
    Next
    INDEX
    Explanations

    text formatting delimiters

    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
    Negative Logits
    ��
    -0.06
    _
    -0.06
    ä¹
    -0.06
    elf
    -0.06
    éĶ
    -0.06
    äºĪ
    -0.06
    1
    -0.06
    Ł
    -0.06
    ä½ľ
    -0.06
    A
    -0.06
    POSITIVE LOGITS
    0.10
    åħ¶äºĭ
    0.09
    ()?.
    0.08
    ç«ĭåį³ä¸ĭè½½
    0.08
    /ay
    0.08
    漩
    0.08
    /lg
    0.08
    гей
    0.08
    ëŀĺ
    0.08
    utsal
    0.07
    Activations Density 0.441%

    No Known Activations