© 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. 1094
    Prev
    Next
    INDEX
    Explanations

    certain titles

    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
    æĢ»æľī
    -0.07
    èĩ´çļĦ
    -0.07
    å¹³åľ°
    -0.06
    iero
    -0.06
    itz
    -0.06
    èĩ´
    -0.06
    .Compute
    -0.06
    çĶŁæķĪåIJİ
    -0.06
    indre
    -0.06
    Mage
    -0.06
    POSITIVE LOGITS
    ä¸Ģæ¦Ĥ
    0.09
    rott
    0.08
     qualifies
    0.08
    ä¸įèĥ½ä½ľä¸º
    0.08
    æŁIJäºĽ
    0.07
    åĩ¡
    0.07
    æīĢåĪĹ
    0.07
     certain
    0.07
    áĥ§áĥĿ
    0.07
     Certain
    0.07
    Activations Density 0.123%

    No Known Activations