© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    beliefs or opinions

    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
    âģİ
    -0.26
    iá»ĩn
    -0.23
    =".$_
    -0.22
    /MM
    -0.22
    :numel
    -0.22
    ujÄħce
    -0.22
    straction
    -0.22
    .'_
    -0.22
    ilor
    -0.21
    olta
    -0.21
    POSITIVE LOGITS
     consc
    0.23
    éļ¶å±ŀ
    0.20
     influ
    0.19
     affid
    0.19
     suspension
    0.19
    è¾ħ导åijĺ
    0.19
    è¿¥
    0.19
    æĿĪ
    0.19
    signin
    0.18
     Kontakt
    0.18
    Activations Density 0.001%

    No Known Activations