© 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. 13815
    Prev
    Next
    INDEX
    Explanations

    I + 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
    asseur
    -0.09
    olutely
    -0.08
    orld
    -0.08
    ÑģлÑĮ
    -0.08
    ught
    -0.08
    irement
    -0.08
    rador
    -0.08
    odle
    -0.08
    NamedQuery
    -0.08
    UGHT
    -0.08
    POSITIVE LOGITS
    unya
    0.07
    sWith
    0.07
    .e
    0.07
    wai
    0.07
    fs
    0.07
    ths
    0.06
    ete
    0.06
    ks
    0.06
    ci
    0.06
    åĪĩçļĦ
    0.06
    Activations Density 0.195%

    No Known Activations