© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    math and code

    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
    è¿ľ
    -0.20
    åıĺåİĭ
    -0.20
    achs
    -0.20
    ColumnType
    -0.19
    |--------------------------------------------------------------------------↵
    -0.19
    ahoo
    -0.19
    åij£
    -0.19
    gunakan
    -0.18
    .requires
    -0.18
    æĹ¥è®¯
    -0.18
    POSITIVE LOGITS
    enticate
    0.20
    /////
    0.19
    /-
    0.19
     dÆ°Æ¡ng
    0.19
    æĭĹ
    0.18
    åįļ
    0.18
    æīĭæľºçīĪ
    0.18
    @FindBy
    0.18
    !=-
    0.18
    ëŀĦ
    0.18
    Activations Density 0.133%

    No Known Activations