© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3809
    Prev
    Next
    INDEX
    Explanations

    insects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     มà¸ģราà¸Ħม
    -0.20
     Jeg
    -0.19
    骢
    -0.19
    çĭ¸
    -0.19
    æĿĤ
    -0.19
     Rihanna
    -0.18
    icipants
    -0.18
    äºĨ好å¤ļ
    -0.18
    驯
    -0.18
    __.__
    -0.18
    POSITIVE LOGITS
    æĺĨèĻ«
    0.28
     insects
    0.26
     insect
    0.25
    icides
    0.23
     resil
    0.23
    mouseenter
    0.22
    èļ¨
    0.22
    	freopen
    0.21
    éĵĹ
    0.21
     Bite
    0.21
    Activations Density 0.761%

    No Known Activations