© 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. 39413
    Prev
    Next
    INDEX
    Explanations

    web content: ADVERTISEMENT, tickets, Websites, Director

    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
    åįģåħŃç«ł
    -0.06
    æľīæĪij
    -0.06
    å¼¹
    -0.06
    ç¢į
    -0.06
    åı¯èĥ½å°±
    -0.06
    ucene
    -0.06
    èķī
    -0.06
    ekat
    -0.06
    åIJİåıĪ
    -0.06
    ä¸įèµ·æĿ¥
    -0.06
    POSITIVE LOGITS
    "":
    0.08
    )':
    0.08
    oret
    0.08
    "&
    0.07
    èĢį
    0.07
    ادÙĩ
    0.07
    ADVERTISEMENT
    0.07
    qués
    0.07
    ìĪŃ
    0.07
    tickets
    0.07
    Activations Density 0.079%

    No Known Activations