© 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. 45758
    Prev
    Next
    INDEX
    Explanations

    loops and iteration constructs

    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
    fig
    -0.08
    bra
    -0.07
    amol
    -0.07
    ä¸į足ä¹ĭå¤Ħ
    -0.07
    ipas
    -0.07
    ust
    -0.07
    ces
    -0.06
    ä¸įåĸĦ
    -0.06
    mac
    -0.06
    ä¹ĭ忧
    -0.06
    POSITIVE LOGITS
    æĭ¬
    0.08
    arka
    0.07
    尿裤
    0.07
    æݥ线
    0.07
    dent
    0.07
    fähigkeit
    0.07
    اپ
    0.07
     kli
    0.07
    ingg
    0.07
    Õ¡Õ½
    0.07
    Activations Density 0.003%

    No Known Activations