© 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. 18483
    Prev
    Next
    INDEX
    Explanations

    meat and flesh

    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
    èij«
    -0.09
    æŁij
    -0.08
    æĬ¹èĮ¶
    -0.08
    éħ¢
    -0.08
    ç°¸
    -0.08
    ivy
    -0.08
    _survey
    -0.07
    -cookie
    -0.07
     kẹo
    -0.07
    ç³ĸæµĨ
    -0.07
    POSITIVE LOGITS
     meat
    0.11
    èĤīçļĦ
    0.11
     мÑıÑģо
    0.10
    çļĦèĤī
    0.09
     мÑıÑģа
    0.09
    èĤīç±»
    0.09
    èĤīè´¨
    0.09
     flesh
    0.09
    èĤī
    0.09
    å±łå®°
    0.09
    Activations Density 0.133%

    No Known Activations