© 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. 40787
    Prev
    Next
    INDEX
    Explanations

    organizational

    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
    s
    -0.08
    ابÙĬØ©
    -0.08
    adiens
    -0.08
    ever
    -0.08
    gether
    -0.07
    ecca
    -0.07
    cidental
    -0.07
    à¸ģ
    -0.07
    еÑĢбÑĥ
    -0.07
    ׳×ķת
    -0.07
    POSITIVE LOGITS
    ÂŃ
    0.09
    inge
    0.09
    annya
    0.08
    0.08
    edly
    0.08
    Åijl
    0.08
    ingly
    0.08
    çĦ¶å¤§
    0.08
    áĥĵáĥIJáĥľ
    0.08
    ings
    0.08
    Activations Density 2.456%

    No Known Activations