© 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. 8702
    Prev
    Next
    INDEX
    Explanations

    quick way or estimation

    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
    áŁĭ
    -0.12
    oggler
    -0.10
    累累
    -0.09
    ذج
    -0.09
    htags
    -0.09
    incerely
    -0.09
    à¸ģารà¹Ģà¸ĩิà¸Ļ
    -0.09
    ContentLoaded
    -0.08
    łĢ
    -0.08
    htag
    -0.08
    POSITIVE LOGITS
    lime
    0.11
    silver
    0.09
    ly
    0.09
    stens
    0.09
    sand
    0.09
    nam
    0.09
    íŀĪ
    0.08
    ened
    0.08
    ity
    0.08
    ãĥ£
    0.08
    Activations Density 0.022%

    No Known Activations