© 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. 10261
    Prev
    Next
    INDEX
    Explanations

    details about or of

    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
    announce
    -0.08
    ifax
    -0.07
    人头
    -0.07
    çļĦéĤ£ä¸ªäºº
    -0.07
    /of
    -0.07
    æł·
    -0.07
     heck
    -0.07
    çĥĽåħī
    -0.07
    大æķ°æį®åĪĨæŀIJ
    -0.07
    åĨĮ
    -0.07
    POSITIVE LOGITS
    upe
    0.08
    à¸Ķีà¸ģวà¹Īา
    0.07
    å°±æĺ¯äºĨ
    0.07
    »:
    0.07
    uale
    0.07
    áĥ
    0.07
    ork
    0.07
     à¸Ķัà¸ĩà¸Ļีà¹ī
    0.07
    åĿĩ以
    0.06
    uhi
    0.06
    Activations Density 0.006%

    No Known Activations