© 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. 3673
    Prev
    Next
    INDEX
    Explanations

    Inner or specific

    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
    ropri
    -0.25
    )="
    -0.21
    )did
    -0.21
    loquent
    -0.20
    usher
    -0.20
    rott
    -0.20
    SError
    -0.19
    imary
    -0.19
    )((((
    -0.19
    >NN
    -0.19
    POSITIVE LOGITS
     Inner
    0.21
    åħĭæĢĿ
    0.21
     Fuji
    0.20
    ISTRIBUT
    0.20
    /sweetalert
    0.20
    个çĻ¾åĪĨ
    0.20
     Giuliani
    0.20
     INNER
    0.20
    ðŁĵĪ
    0.20
     coaching
    0.20
    Activations Density 0.658%

    No Known Activations