© 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. 31391
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    à¸ŀิ
    -0.08
     длиной
    -0.08
    éķ¿åº¦ä¸º
    -0.08
    abox
    -0.08
    -register
    -0.08
     lengths
    -0.07
    尺度
    -0.07
    çļĦ身
    -0.07
    irus
    -0.07
    onsor
    -0.07
    POSITIVE LOGITS
     percentage
    0.22
     percentages
    0.21
     (%)
    0.21
    çĻ¾åĪĨæ¯Ķ
    0.21
    percentage
    0.21
    çĻ¾åĪĨä¹ĭ
    0.19
     Percentage
    0.18
     percent
    0.18
     пÑĢоÑĨенÑĤ
    0.18
    Percentage
    0.18
    Activations Density 0.289%

    No Known Activations