© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ournemouth
    -0.27
    ä»Ģä¹ĪåİŁåĽł
    -0.23
    ÃŃculo
    -0.21
    llu
    -0.21
    edBy
    -0.20
    ìĪĻ
    -0.20
    .clientHeight
    -0.20
    .ObjectModel
    -0.20
    gnore
    -0.20
    羣çĪ±
    -0.19
    POSITIVE LOGITS
     as
    0.39
    为ä¾ĭ
    0.29
    为åĩĨ
    0.28
    为å¥ijæľº
    0.28
    å°½åı¯èĥ½
    0.26
    为主
    0.25
    ä¸ºçĽ®çļĦ
    0.24
    为主线
    0.24
    为æĬĵæīĭ
    0.23
     quanto
    0.23
    Activations Density 0.133%

    No Known Activations