© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 40
    Prev
    Next
    INDEX
    Explanations

    probability problems

    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
    arpa
    -0.20
    exampleInputEmail
    -0.20
    @Json
    -0.20
    avit
    -0.20
     holland
    -0.20
    indsay
    -0.19
    VersionUID
    -0.19
    sigmoid
    -0.19
    æĹ¥æĬ¥è®°èĢħ
    -0.18
    纨
    -0.18
    POSITIVE LOGITS
    ·¸
    0.22
     cellFor
    0.22
    asurer
    0.21
    >window
    0.21
     Erectile
    0.21
     FROM
    0.20
    ETYPE
    0.20
    /from
    0.20
    .RelativeLayout
    0.20
     from
    0.20
    Activations Density 0.048%

    No Known Activations