© 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. 47909
    Prev
    Next
    INDEX
    Explanations

    complicating geometrical

    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
    empel
    -0.07
    apura
    -0.06
    amus
    -0.06
    rib
    -0.06
    ç¹ģ
    -0.05
    å¥ī
    -0.05
    èѬ
    -0.05
    åĿĩ
    -0.05
    cept
    -0.05
    æĮº
    -0.05
    POSITIVE LOGITS
    orsi
    0.09
    æıIJåīįåģļ好
    0.08
    éĤ£ä¸įæĺ¯
    0.08
    è¿Ļä¼ļ
    0.08
    è¿Ļåı¯èĥ½
    0.08
    åĬłå¼ºå¯¹
    0.08
    å°±åıĪ
    0.08
    ä¼ļå½±åĵįåĪ°
    0.08
    åı¯èĥ½å¯¼èĩ´
    0.08
    类似éĹ®é¢ĺ
    0.08
    Activations Density 0.005%

    No Known Activations