© 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. 46344
    Prev
    Next
    INDEX
    Explanations

    diffusion, suppress, collaboration

    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
    _ATTRIB
    -0.08
    áĭį
    -0.07
    vertime
    -0.07
    åİĨåİĨ
    -0.07
    saan
    -0.07
    ÙĨدÙĩ
    -0.07
    çİ°å°Ĩæľīåħ³äºĭ项
    -0.07
    achu
    -0.07
    undy
    -0.07
    igni
    -0.07
    POSITIVE LOGITS
    èĬ®
    0.06
     رÙģ
    0.06
    åĽŀçļĦ
    0.06
    amba
    0.06
    oh
    0.06
     light
    0.06
    ano
    0.06
    ob
    0.06
    inn
    0.06
    ÑģÑĤв
    0.06
    Activations Density 0.286%

    No Known Activations