© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46154
    Prev
    Next
    INDEX
    Explanations

    born followed by dates

    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
    unami
    -0.08
    åij¨ä¸Ģèĩ³
    -0.08
    اعت
    -0.08
    å·´æĭī
    -0.08
    ınca
    -0.07
    éĩij森
    -0.07
    uka
    -0.07
    åĽŀæµģ
    -0.07
    aian
    -0.07
     swinger
    -0.07
    POSITIVE LOGITS
    æľĽè¿ľ
    0.08
    retch
    0.08
    åħ¬å¼ı
    0.07
    £
    0.06
     expert
    0.06
    ilm
    0.06
    ynn
    0.06
    สูà¸ķร
    0.06
     Expansion
    0.06
    hiri
    0.06
    Activations Density 0.002%

    No Known Activations