© 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. 23652
    Prev
    Next
    INDEX
    Explanations

    Home vendors

    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
    olik
    -0.08
    yon
    -0.07
    ÙĨز
    -0.07
    NN
    -0.07
    漸
    -0.07
    èĩªéĢĤåºĶ
    -0.07
    omia
    -0.07
    itut
    -0.07
     Cang
    -0.07
    beutel
    -0.07
    POSITIVE LOGITS
     reckon
    0.07
    à¹Ģà¸Ķีà¹Īยว
    0.07
    æĮīåħ¶
    0.07
     undertaking
    0.07
    åĽłåħ¶
    0.07
    æīĭãģĮ
    0.06
    ibase
    0.06
    éĶ£é¼ĵ
    0.06
     darn
    0.06
     liberation
    0.06
    Activations Density 0.001%

    No Known Activations