© 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. 49684
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    ablish
    -0.07
    igan
    -0.07
    felder
    -0.07
    eenth
    -0.06
    åıĮä¸Ģæµģ
    -0.06
    [input
    -0.06
    äººä¸ºæľ¬
    -0.06
     reb
    -0.06
    resh
    -0.06
    áĥ£áĥľ
    -0.06
    POSITIVE LOGITS
    awas
    0.08
    åĩĨ
    0.07
    емов
    0.07
    åĿ
    0.07
    GOP
    0.07
    åħ¨ä½ĵå¹²éĥ¨èģĮå·¥
    0.06
     загÑĢ
    0.06
    inov
    0.06
    æĹ¶è®¸
    0.06
    ién
    0.06
    Activations Density 0.386%

    No Known Activations