© 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. 64550
    Prev
    Next
    INDEX
    Explanations

    there is/are/exists

    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
    ness
    -0.16
    Ø©
    -0.09
    ryption
    -0.09
    RARY
    -0.09
    eldes
    -0.09
    queda
    -0.09
    ulate
    -0.09
    ation
    -0.08
    ature
    -0.08
    sson
    -0.08
    POSITIVE LOGITS
    es
    0.10
    an
    0.10
    en
    0.10
    Ùĩ
    0.09
    abouts
    0.09
    ed
    0.09
    on
    0.09
    äºĨ
    0.08
    u
    0.08
    al
    0.08
    Activations Density 0.107%

    No Known Activations