© 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. 11904
    Prev
    Next
    INDEX
    Explanations

    HTML tags and documentation markers

    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
     tie
    -0.06
    i
    -0.06
    -se
    -0.06
    ént
    -0.06
     ch
    -0.06
    æĺ¯ä¸ŃåĽ½
    -0.06
    ÙģتÙĩ
    -0.06
     aboard
    -0.06
    id
    -0.06
    '
    -0.06
    POSITIVE LOGITS
    Ñĥл
    0.09
    微信æī«ä¸Ģæī«
    0.09
    saan
    0.09
    _MEMBERS
    0.08
    пелÑĮ
    0.08
    urb
    0.08
    ezett
    0.08
    acea
    0.08
    agra
    0.08
    Backing
    0.08
    Activations Density 0.059%

    No Known Activations