© 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. 14507
    Prev
    Next
    INDEX
    Explanations

    code-like punctuation and structure

    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
    ibat
    -0.08
    å¿ħé¡»çĶ±
    -0.07
    åĿĬ
    -0.07
    plica
    -0.07
    åľ°åĮºåĴĮ
    -0.07
    æļĤè¡Į
    -0.07
    ä¸įäºĪåıĹçIJĨ
    -0.07
    å¸ħ
    -0.07
    ond
    -0.07
    UEL
    -0.07
    POSITIVE LOGITS
    ilie
    0.08
    èĥ½å¤Łæ»¡è¶³
    0.07
    æľīèĥ½åĬĽ
    0.07
    èĥ½æ»¡è¶³
    0.07
    ìľłìĿĺ
    0.07
    igner
    0.07
    ä¸įèĥ½æ»¡è¶³
    0.07
    ä»Ģä¹Īäºĭæĥħ
    0.07
    å¯¹æľ¬æ¬¡
    0.07
    æīĢæıIJä¾ĽçļĦ
    0.07
    Activations Density 0.294%

    No Known Activations