© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21573
    Prev
    Next
    INDEX
    Explanations

    alpha, normal, entries, BIN, cell, rotation, size

    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
    æľ¬ç½ijç«Ļ
    -0.07
    æĺ¯ä¸ĢéŨ
    -0.07
     sight
    -0.06
    jó
    -0.06
    ty
    -0.06
     lightweight
    -0.06
    æįŁçĽĬ
    -0.06
    uxt
    -0.06
    å¯ĩ
    -0.06
    erb
    -0.06
    POSITIVE LOGITS
    åİ»
    0.07
    áng
    0.07
    å®ŀéĻħ
    0.07
     Eins
    0.07
    enn
    0.07
    æłijä¸Ģ
    0.07
     Oster
    0.07
    ument
    0.07
    enna
    0.07
    åį³
    0.07
    Activations Density 0.008%

    No Known Activations