© 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. 29432
    Prev
    Next
    INDEX
    Explanations

    +1

    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
    ÑĢаÑĩи
    -0.07
    ables
    -0.07
    ogos
    -0.07
    èģĶåIJĪåĪĽå§ĭ人
    -0.06
    rick
    -0.06
    ats
    -0.06
     vĩ
    -0.06
    è°ģçŁ¥éģĵ
    -0.06
    alj
    -0.06
    å°ıåĪ°
    -0.06
    POSITIVE LOGITS
    Authorize
    0.08
    å¤§æľ¬
    0.07
    asc
    0.07
    oine
    0.06
    /loading
    0.06
    teles
    0.06
    人ãĤĴ
    0.06
    cesi
    0.06
     parad
    0.06
    人们对
    0.06
    Activations Density 0.010%

    No Known Activations