© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9086
    Prev
    Next
    INDEX
    Explanations

    business and technical contexts

    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
    -bars
    -0.08
    Ñģени
    -0.08
    ffer
    -0.08
    nder
    -0.08
    ãĥĨãĤ£ãĥĥãĤ¯
    -0.08
    inger
    -0.07
    imuth
    -0.07
    upro
    -0.07
    åħĭ森
    -0.07
    aranto
    -0.07
    POSITIVE LOGITS
    /
    0.08
    xp
    0.07
    -
    0.06
    路西
    0.06
    pl
    0.06
    à¸ŀล
    0.06
    éĿ¢è²Į
    0.06
    +
    0.06
    FW
    0.06
     oriented
    0.06
    Activations Density 1.296%

    No Known Activations