© 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. 47155
    Prev
    Next
    INDEX
    Explanations

    idealized picture

    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
     prevision
    -0.08
    åĢĶ
    -0.08
    éļıåľ°
    -0.08
    inky
    -0.08
    elon
    -0.07
    ateral
    -0.07
    æ¯ı天
    -0.07
     heartbreaking
    -0.07
     aggravated
    -0.07
     gespannt
    -0.07
    POSITIVE LOGITS
     ideal
    0.09
    çIJĨæĥ³
    0.09
    ideal
    0.08
    åIJĪæ³ķæĢ§
    0.08
     image
    0.08
    çļĦçIJĨæĥ³
    0.08
     virt
    0.08
    符åIJĪåĽ½å®¶
    0.08
    çIJĨæĥ³çļĦ
    0.07
    ç¾İå¾·
    0.07
    Activations Density 0.100%

    No Known Activations