© 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. 40396
    Prev
    Next
    INDEX
    Explanations

    digital values, executable files, .tex files

    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
    oure
    -0.07
    FFE
    -0.07
    亲亲
    -0.07
    ouro
    -0.06
    roit
    -0.06
    å¾ģ
    -0.06
    ignano
    -0.06
    大å¼Ģ
    -0.06
    hatt
    -0.06
     Origin
    -0.06
    POSITIVE LOGITS
     afterwards
    0.11
     afterward
    0.10
     Returned
    0.10
     returned
    0.10
    åĩºæĿ¥åIJİ
    0.10
     subsequently
    0.09
    à¸Ĺีà¹Īà¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    0.09
    åIJİç»ŃçļĦ
    0.09
     اÙĦÙĨات
    0.09
    .uf
    0.09
    Activations Density 0.177%

    No Known Activations