© 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. 21928
    Prev
    Next
    INDEX
    Explanations

    words related to professions and concepts

    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
    обо
    -0.07
    å°ı说ç½ij
    -0.06
    _endian
    -0.06
    arer
    -0.06
    íĻĶëIJľ
    -0.06
     Bong
    -0.06
    Ess
    -0.06
    ìłģìľ¼ë¡ľ
    -0.06
    BSD
    -0.06
    ä¸ĩå¥Ĺ
    -0.06
    POSITIVE LOGITS
    ersatz
    0.08
    haus
    0.07
     democr
    0.07
    éĻ¤æѤ
    0.07
    å®ĺ
    0.07
    ught
    0.07
    龸
    0.07
    aska
    0.07
    noinspection
    0.07
    ceph
    0.07
    Activations Density 0.361%

    No Known Activations