© 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. 19570
    Prev
    Next
    INDEX
    Explanations

    Mojibake and Russian/English words

    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
    ä»»ä½ķè´¹çĶ¨
    -0.08
    uto
    -0.08
    inos
    -0.08
    大åĮħ
    -0.08
    ä½Ĩä¹Ł
    -0.07
    éĿŀ常å¤ļçļĦ
    -0.07
    ä½Ĩä¹Łæľī
    -0.07
    äll
    -0.07
    èĢħ们
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
    /how
    0.10
    soever
    0.10
     Ñģаме
    0.09
    upon
    0.09
    以åıĬå¦Ĥä½ķ
    0.08
     ÙĪÙĥÙĬÙģ
    0.08
     именно
    0.08
    ëĵłì§Ģ
    0.08
    quam
    0.08
    isky
    0.08
    Activations Density 0.003%

    No Known Activations