© 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. 60814
    Prev
    Next
    INDEX
    Explanations

    current + noun

    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
    (es
    -0.09
    Æł
    -0.08
    ÙĪÚº
    -0.08
    åIJİéĿ¢çļĦ
    -0.08
     eventually
    -0.08
    otin
    -0.08
    åIJİæĿ¥çļĦ
    -0.07
    å½ĵæŶçļĦ
    -0.07
    etic
    -0.07
    èĩªæѤ
    -0.07
    POSITIVE LOGITS
    åĴĮæľªæĿ¥
    0.14
    /current
    0.10
    为æŃ¢
    0.10
    -day
    0.10
    ledge
    0.09
    -current
    0.09
    ly
    0.09
    çĤºæŃ¢
    0.09
    çĬ¶åĨµ
    0.09
    adays
    0.09
    Activations Density 0.125%

    No Known Activations