© 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. 38021
    Prev
    Next
    INDEX
    Explanations

    `)} $`

    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
     =$
    -0.08
    ZA
    -0.07
    ZW
    -0.07
    çļĦæĸ¹æ³ķæĺ¯
    -0.06
    YW
    -0.06
    wed
    -0.06
    loh
    -0.06
    ont
    -0.06
    æĶ¶å®¹
    -0.06
    owa
    -0.06
    POSITIVE LOGITS
    raad
    0.07
    pir
    0.07
    ansom
    0.07
    cker
    0.07
    .Then
    0.07
    髦
    0.07
    éĤ£ä¹Īåľ¨
    0.07
     mitra
    0.07
    efore
    0.07
    ogne
    0.07
    Activations Density 0.012%

    No Known Activations