© 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. 18512
    Prev
    Next
    INDEX
    Explanations

    try to (unsuccessfully)

    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
    ÙĬات
    -0.09
    arity
    -0.09
    adÃŃ
    -0.09
    æv
    -0.09
    quê
    -0.08
    voli
    -0.08
    indel
    -0.08
    à¥įन
    -0.08
    aisser
    -0.08
    ilhar
    -0.08
    POSITIVE LOGITS
     unsuccessfully
    0.11
    ar
    0.09
     vain
    0.08
    pt
    0.07
    "
    0.07
     desperately
    0.07
     futile
    0.07
    åĴĮåĬªåĬĽ
    0.07
     nghiá»ĩm
    0.06
    ed
    0.06
    Activations Density 0.152%

    No Known Activations