© 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. 61199
    Prev
    Next
    INDEX
    Explanations

    words, topics, or games

    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
    ::-
    -0.08
    æ»ĭ
    -0.08
    ulton
    -0.07
    arz
    -0.07
    _inline
    -0.07
    angan
    -0.07
    eben
    -0.07
    ادا
    -0.07
    ploi
    -0.07
    plied
    -0.07
    POSITIVE LOGITS
     alone
    0.08
    çĭ¬åįł
    0.08
    ä¸İåħ¶ä»ĸ
    0.07
    å¿ħ
    0.07
    alone
    0.07
    åĩºåıij
    0.07
    èĤ¯å®ļè¦ģ
    0.07
    æĪĸ缺
    0.07
    åıĤä¸İçļĦ
    0.07
    èĩ³å°ij
    0.06
    Activations Density 0.027%

    No Known Activations