© 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. 62749
    Prev
    Next
    INDEX
    Explanations

    residual errors

    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
     mil
    -0.07
    注åĨĮèµĦéĩij
    -0.07
    OperationException
    -0.06
    fino
    -0.06
     masculine
    -0.06
    Mil
    -0.06
    åħ¸
    -0.06
     endurance
    -0.06
     Mil
    -0.06
    edar
    -0.06
    POSITIVE LOGITS
     residuals
    0.13
    Squared
    0.09
    /errors
    0.09
    æ®ĭ
    0.08
    agged
    0.08
    éĢıäºĨ
    0.08
     tá»ĩ
    0.08
    -errors
    0.08
     demean
    0.08
    avanaugh
    0.08
    Activations Density 0.006%

    No Known Activations