© 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. 12808
    Prev
    Next
    INDEX
    Explanations

    food ingredients

    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
     Thought
    -0.08
    ungen
    -0.07
    è°ģä¹Ł
    -0.07
     thought
    -0.07
    jections
    -0.07
    ouro
    -0.07
    è¡¥è¡Ģ
    -0.06
    ZO
    -0.06
    èIJ½
    -0.06
    eby
    -0.06
    POSITIVE LOGITS
    çļĦéĢīæĭ©
    0.14
    éĢīæĭ©åľ¨
    0.13
    éĢīæĭ©ä¸į
    0.12
    å°½éĩıéĢīæĭ©
    0.12
    æľĢ好æĺ¯
    0.12
    éĢīæĭ©åĴĮ
    0.11
    éĢīæĭ©åIJĪéĢĤçļĦ
    0.11
    éĢīçĶ¨
    0.11
     chosen
    0.11
    éĢīæĭ©
    0.11
    Activations Density 0.117%

    No Known Activations