© 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. 3617
    Prev
    Next
    INDEX
    Explanations

    given that, calculated from

    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
    ellone
    -0.09
    cpy
    -0.07
    .cn
    -0.07
    yntax
    -0.07
    uges
    -0.07
    à¹Īà¸Ńม
    -0.07
    ill
    -0.07
    usse
    -0.07
    æīĢ产çĶŁçļĦ
    -0.06
    ontaine
    -0.06
    POSITIVE LOGITS
    à¹Ħà¸Ķà¹īà¸Īาà¸ģ
    0.12
     via
    0.09
    à¸Īาà¸ģà¸ģาร
    0.09
    _from
    0.08
    åı¯ä»İ
    0.08
    缴æİ¥ä»İ
    0.08
    from
    0.08
    éĢļè¿ĩä¸İ
    0.08
     using
    0.08
     from
    0.08
    Activations Density 0.072%

    No Known Activations