© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    plus, y, squared terms

    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
    ÑĦÑĥ
    -0.08
    goro
    -0.07
    endas
    -0.06
    &action
    -0.06
    ÑĢави
    -0.06
    ippo
    -0.06
    enance
    -0.06
    raca
    -0.06
    <class
    -0.06
    åij±åij±
    -0.06
    POSITIVE LOGITS
    åĬłä¸Ĭ
    0.07
    asco
    0.07
    è´¡çĮ®
    0.06
    沿çĿĢ
    0.06
     plus
    0.06
    itted
    0.06
    erson
    0.06
    ÏħÏĩ
    0.06
    rys
    0.06
    æĭł
    0.06
    Activations Density 0.003%

    No Known Activations