© 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. 33159
    Prev
    Next
    INDEX
    Explanations

    table headers

    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
    大æľī
    -0.06
    c
    -0.06
    ,
    -0.06
    xxx
    -0.06
    cepts
    -0.06
    以任ä½ķ
    -0.06
    ix
    -0.06
    p
    -0.06
    —
    -0.06
    çĶ¨æĦı
    -0.06
    POSITIVE LOGITS
    leman
    0.09
     rowspan
    0.08
    Unnamed
    0.08
    æľĢæĸ°è¯Ħ论
    0.08
     bersangkutan
    0.08
    åĪ°æĿ¥çļĦ
    0.08
    oja
    0.08
    nable
    0.08
    à¹Ģà¸Ńà¸ĩ
    0.08
    eminen
    0.08
    Activations Density 0.015%

    No Known Activations