© 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. 11175
    Prev
    Next
    INDEX
    Explanations

    palladium catalysts

    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
    alute
    -0.07
    ihad
    -0.07
    æ¿Ģ
    -0.07
    ¾
    -0.06
    ç²Ĺç²®
    -0.06
    격
    -0.06
     chilling
    -0.06
    éĨĴäºĨ
    -0.06
    orial
    -0.06
     waking
    -0.06
    POSITIVE LOGITS
    çĺ¤
    0.09
    irth
    0.08
    è¡«
    0.08
     persa
    0.07
    æ¯Ĵèį¯
    0.07
    æ²¼
    0.07
    arat
    0.07
    cini
    0.07
    aris
    0.07
     poisoned
    0.07
    Activations Density 0.016%

    No Known Activations