© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    open

    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
    æĪijæĬĬ
    -0.21
    <algorithm
    -0.21
    repr
    -0.19
     prer
    -0.19
    æ¦Ĥæĭ¬
    -0.19
    же
    -0.19
    è§Ĭ
    -0.19
     mik
    -0.19
    å¥ĩçijŀ
    -0.19
     anzeigen
    -0.19
    POSITIVE LOGITS
    lke
    0.32
    благо
    0.30
    alborg
    0.26
    å¼ıçļĦ
    0.25
    ended
    0.25
     minded
    0.25
    -Trump
    0.25
     scarc
    0.25
    ksam
    0.25
    rels
    0.25
    Activations Density 0.064%

    No Known Activations