© 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. 3438
    Prev
    Next
    INDEX
    Explanations

    under

    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
    .Butter
    -0.23
    entiful
    -0.22
    rippling
    -0.22
    ",-
    -0.22
    &&!
    -0.21
    @show
    -0.21
    .VideoCapture
    -0.21
    ocache
    -0.21
    ennifer
    -0.20
    acists
    -0.20
    POSITIVE LOGITS
     èĩªåĬ¨çĶŁæĪIJ
    0.31
     circumstances
    0.30
     Conditions
    0.28
    æĿ¡ä»¶ä¸ĭ
    0.28
     conditions
    0.26
     under
    0.26
    æĿ¡ä»¶
    0.25
    Conditions
    0.24
    conditions
    0.23
     guise
    0.23
    Activations Density 0.175%

    No Known Activations