© 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. 28883
    Prev
    Next
    INDEX
    Explanations

    approximately

    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
    /her
    -0.13
    er
    -0.13
    erat
    -0.09
    /or
    -0.09
    erot
    -0.09
    gable
    -0.08
    ième
    -0.08
    fold
    -0.08
    erio
    -0.08
    uly
    -0.08
    POSITIVE LOGITS
    ï¸İ
    0.13
    ï¸ı
    0.10
    imated
    0.10
     nhau
    0.09
    imates
    0.08
    imating
    0.08
     halnya
    0.08
    imations
    0.08
    åħ¶
    0.07
    à¸ģารà¸ĵà¹Į
    0.07
    Activations Density 0.001%

    No Known Activations