© 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. 21218
    Prev
    Next
    INDEX
    Explanations

    imaginary direction

    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
    å«ī
    -0.09
    濯
    -0.08
     chua
    -0.08
    漩
    -0.08
    деÑĤÑĮ
    -0.08
    /cop
    -0.08
    ilage
    -0.07
     ÙĦÙħس
    -0.07
    aal
    -0.07
    opus
    -0.07
    POSITIVE LOGITS
    à¹īาà¸Ļ
    0.07
    åĴĮå¹³
    0.06
    urn
    0.06
    åĮºå¸Ĥ
    0.06
    itera
    0.06
    à¶Ń
    0.06
    æľĭ
    0.06
     cảnh
    0.06
    项
    0.06
    beer
    0.06
    Activations Density 0.001%

    No Known Activations