© 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. 60480
    Prev
    Next
    INDEX
    Explanations

    and creates

    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
     due
    -0.07
    нва
    -0.07
    èĢģåİ»
    -0.07
    ساÙĦ
    -0.07
    ä¸ŃåĽ½å¸Ĥåľº
    -0.07
    env
    -0.06
    ':''
    -0.06
    lacer
    -0.06
    нке
    -0.06
     rendelkez
    -0.06
    POSITIVE LOGITS
    ä»İèĢĮ
    0.09
    ä»İèĢĮ导èĩ´
    0.09
    ä»İèĢĮ使
    0.09
    使å¾Ĺ
    0.07
    nies
    0.07
    åĨįåĬłä¸Ĭ
    0.07
     wiederum
    0.07
    导èĩ´
    0.07
    çIJĨ论ä¸Ĭ
    0.07
    ä¸Ģæĸ¹éĿ¢
    0.07
    Activations Density 0.027%

    No Known Activations