© 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. 3916
    Prev
    Next
    INDEX
    Explanations

    Here are some

    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
    antasy
    -0.07
    èĩªèº«çļĦ
    -0.07
    éħįç½®æĸ¹éĿ¢
    -0.07
    gara
    -0.07
    请ä¸ĭè½½
    -0.07
    å¦Ĥæŀľè¯´
    -0.07
    usak
    -0.07
    cae
    -0.07
    åĺīå¹´åįİ
    -0.07
    nic
    -0.06
    POSITIVE LOGITS
    åIJĦç»Ħ
    0.08
     key
    0.08
    олее
    0.08
    åħ³éĶ®çļĦ
    0.08
    haltung
    0.07
    ло
    0.07
    åĩłç§į
    0.06
     наиболее
    0.06
     SHALL
    0.06
    omi
    0.06
    Activations Density 0.114%

    No Known Activations