© 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. 26066
    Prev
    Next
    INDEX
    Explanations

    studies, create, or leak like a sieve

    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
    æĥ³åĪ°è¿ĻéĩĮ
    -0.08
    ëŁ¼
    -0.07
    ringen
    -0.07
    åĭĻ
    -0.07
    kens
    -0.07
    লাম
    -0.07
    ä¹Łè®©æĪij
    -0.07
    Wildcard
    -0.07
    bergen
    -0.07
    лаго
    -0.07
    POSITIVE LOGITS
    -Mar
    0.07
    æĪĸèĢħ说
    0.06
    .Framework
    0.06
    æķij
    0.06
    å®ĥçļĦ
    0.06
    oce
    0.06
    å®ĥéĤ£
    0.06
    its
    0.06
    漫
    0.06
    OrDefault
    0.06
    Activations Density 1.019%

    No Known Activations