© 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. 13420
    Prev
    Next
    INDEX
    Explanations

    cofactors, enzymes, and biochemicals

    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
    ophobia
    -0.07
    æĶ¶æ²»
    -0.07
    gw
    -0.07
    æ±ĤçĶŁåŃĺ
    -0.07
    رار
    -0.07
     crackdown
    -0.07
    åĨ²çĿĢ
    -0.07
    æĻ¶ç¡ħ
    -0.07
    äºķ
    -0.07
    sstr
    -0.07
    POSITIVE LOGITS
     intermedi
    0.08
    åĤ³éģŀ
    0.08
    为载ä½ĵ
    0.08
    åıĤä¸İ
    0.08
     поÑģÑĢед
    0.08
     intermediary
    0.08
    itty
    0.08
    -transfer
    0.08
     shuttle
    0.08
    ä¸ĵèģĮ
    0.08
    Activations Density 0.052%

    No Known Activations