© 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. 50703
    Prev
    Next
    INDEX
    Explanations

    log(n)

    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
    à¦Łà§ĩ
    -0.10
    issi
    -0.09
    horn
    -0.09
    大讲åłĤ
    -0.09
    ãĥ¬ãĥĥãĥĪ
    -0.08
    áĢĻáĢºáĢ¸
    -0.08
    CKER
    -0.08
    iono
    -0.08
    istra
    -0.08
    åIJįæĢĿ
    -0.08
    POSITIVE LOGITS
    è¥
    0.06
    âĢİ
    0.06
    0.06
    ↵
    0.06
    2
    0.05
    odob
    0.05
    "
    0.05
    ç§
    0.05
    ↵↵
    0.05
    ''
    0.05
    Activations Density 0.006%

    No Known Activations