© 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. 51522
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    adop
    -0.08
    áĥĶáĥķ
    -0.07
    aroo
    -0.07
    onnier
    -0.07
    odar
    -0.07
    fäh
    -0.07
    åĽĽä¸ªèĩªä¿¡
    -0.07
    amay
    -0.07
     ฯ
    -0.07
    YPD
    -0.07
    POSITIVE LOGITS
     Cummings
    0.07
    plet
    0.07
    uffer
    0.07
    翼
    0.06
    _tpl
    0.06
    ,
    0.06
    ,.
    0.06
    asser
    0.06
    utdown
    0.06
    以赴
    0.06
    Activations Density 0.004%

    No Known Activations