© 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. 26729
    Prev
    Next
    INDEX
    Explanations

    to verb

    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
    jenigen
    -0.07
    说è¦ģ
    -0.07
    ÑĩеÑĢед
    -0.07
    ÑĢаÑģ
    -0.07
    å¤ĩ
    -0.07
    δια
    -0.07
    __(
    -0.07
    appa
    -0.07
    arkt
    -0.06
    баланÑģи
    -0.06
    POSITIVE LOGITS
    /from
    0.10
    asted
    0.10
    asting
    0.09
    plevel
    0.09
    geht
    0.08
    -day
    0.08
    æĿ¥è¶Ĭ
    0.08
     allá
    0.08
     fruition
    0.08
    ppers
    0.08
    Activations Density 0.458%

    No Known Activations