© 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. 14128
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    Responses
    -0.07
    #=
    -0.07
    ibold
    -0.07
    æĸŃæ¡¥
    -0.07
    illian
    -0.07
    idge
    -0.07
    berger
    -0.06
    ä¼ļé¦Ĩ
    -0.06
    isspace
    -0.06
    ulls
    -0.06
    POSITIVE LOGITS
    åħĭæľį
    0.06
    éĩij丹
    0.06
    iker
    0.06
    laje
    0.06
    ugd
    0.06
     Bres
    0.06
    åĮĸ
    0.06
    /licenses
    0.06
    ize
    0.06
     replaced
    0.06
    Activations Density 0.023%

    No Known Activations