© 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. 33683
    Prev
    Next
    INDEX
    Explanations

    historic Harvard buildings

    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
     esclar
    -0.08
     Ùģص
    -0.08
    elli
    -0.08
    _NB
    -0.08
    ellone
    -0.08
    AndUpdate
    -0.07
     Garan
    -0.07
    ÏĮμε
    -0.07
    åħ³éĶ®æĺ¯
    -0.07
    ='./
    -0.07
    POSITIVE LOGITS
    åĩºäºº
    0.07
    gew
    0.07
    请éĹ®
    0.06
    亡
    0.06
    æµ·ä¸Ń
    0.06
    اÙĭ
    0.06
     feature
    0.06
    g
    0.06
    å¦Ĥä½ķéĢļè¿ĩ
    0.06
    åĨĴçĿĢ
    0.06
    Activations Density 0.198%

    No Known Activations