© 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. 3501
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
    æĪĽ
    -0.20
    夯
    -0.19
     swinger
    -0.19
     Kohana
    -0.19
     Babe
    -0.19
     StartCoroutine
    -0.19
     promot
    -0.19
     gode
    -0.19
     raping
    -0.19
    ç®Ģæĺĵ
    -0.19
    POSITIVE LOGITS
    #ad
    0.24
    è¹ģ
    0.24
    emetery
    0.23
    owied
    0.22
    æijĩäºĨ
    0.22
    :maj
    0.22
    gebn
    0.20
     PÃ¥
    0.20
    ancellor
    0.20
    polator
    0.20
    Activations Density 0.001%

    No Known Activations