© 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. 40283
    Prev
    Next
    INDEX
    Explanations

    facts about subjects

    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
    estens
    -0.09
    大åIJį
    -0.09
    -mobile
    -0.09
    æ
    -0.09
    æļ¦
    -0.08
    ارÙĬ
    -0.08
    anmar
    -0.08
    irma
    -0.08
    ehu
    -0.08
    FromBody
    -0.08
    POSITIVE LOGITS
    is
    0.07
     question
    0.07
    ¾
    0.06
    &
    0.06
    ip
    0.06
    IP
    0.06
    ss
    0.06
    ise
    0.06
     #
    0.06
    åIJĽçļĦ
    0.05
    Activations Density 0.004%

    No Known Activations