© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    reau
    -0.21
    1
    -0.20
    2
    -0.20
    lehem
    -0.20
    alement
    -0.20
     STREAM
    -0.20
     stream
    -0.19
     shred
    -0.19
    rew
    -0.19
    Stream
    -0.19
    POSITIVE LOGITS
    :convert
    0.26
     ucwords
    0.25
    /Dk
    0.23
    ;break
    0.23
    läss
    0.23
    éĶª
    0.23
    "group
    0.23
    lässig
    0.23
    bulan
    0.22
    :;↵
    0.22
    Activations Density 0.100%

    No Known Activations