© 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. 343
    Prev
    Next
    INDEX
    Explanations

    titles of media

    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
    æĹĸ
    -0.24
    ç¼±
    -0.24
     incompet
    -0.21
    æ½ĭ
    -0.20
    åħ¼
    -0.20
    åŃľ
    -0.20
    -0.19
    heet
    -0.19
     /*!<
    -0.19
     Registro
    -0.19
    POSITIVE LOGITS
     Ñģдела
    0.24
    vla
    0.21
    ().'/
    0.21
    ě[
    0.21
    @GetMapping
    0.21
     pestic
    0.20
    å¿ĥ仪çļĦ
    0.20
    )(__
    0.20
    âķ®
    0.20
     overwhel
    0.20
    Activations Density 2.758%

    No Known Activations