© 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. 7643
    Prev
    Next
    INDEX
    Explanations

    virulence factors and properties

    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
    ify
    -0.07
    tings
    -0.07
    ãĤ¥
    -0.07
    åĴĢ
    -0.07
    ophilia
    -0.07
    edList
    -0.07
    æĺķ
    -0.07
    upil
    -0.07
    cami
    -0.07
    اث
    -0.07
    POSITIVE LOGITS
    less
    0.12
    LESS
    0.08
    most
    0.08
    gens
    0.08
    estro
    0.08
    à¸ļ
    0.08
    lessness
    0.07
    bok
    0.07
    è¿Ľä¸ĢæŃ¥äºĨ解
    0.07
    å±ĤçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations