© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4068
    Prev
    Next
    INDEX
    Explanations

    cause

    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
    DMETHOD
    -0.28
    >'.↵
    -0.27
    .djang
    -0.25
    .opend
    -0.25
    pta
    -0.25
    /Internal
    -0.23
    ìĻľ
    -0.23
    "<?
    -0.23
    .googlecode
    -0.23
     ,[
    -0.23
    POSITIVE LOGITS
     havoc
    0.23
     renown
    0.23
     maduras
    0.22
     libertin
    0.21
    ffset
    0.20
     penet
    0.20
    ãģ¤ãĤĤãĤĬ
    0.20
     CONSEQUENTIAL
    0.20
     rewind
    0.20
     деÑıÑĤ
    0.19
    Activations Density 0.074%

    No Known Activations