© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    enable/disable

    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
    rvine
    -0.23
    :UITableView
    -0.22
    rowable
    -0.22
    /Dk
    -0.21
     Manning
    -0.21
    èĩªçĶ±
    -0.21
    swire
    -0.20
    |--------------------------------------------------------------------------↵
    -0.20
    esteem
    -0.20
    resizing
    -0.19
    POSITIVE LOGITS
     Leakage
    0.25
     LinearGradient
    0.22
     caz
    0.21
     Feld
    0.21
    ijľ
    0.21
    åĶ
    0.21
    ạy
    0.20
     algu
    0.19
    _AUTO
    0.19
    ODULE
    0.19
    Activations Density 0.125%

    No Known Activations