© 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. 3978
    Prev
    Next
    INDEX
    Explanations

    nature

    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
     Sexo
    -0.23
     agre
    -0.23
    strup
    -0.23
     ActionTypes
    -0.20
    ubern
    -0.20
    indsay
    -0.20
     août
    -0.20
     prostitu
    -0.19
     holland
    -0.19
     novembre
    -0.19
    POSITIVE LOGITS
     natural
    0.35
    èĩªçĦ¶
    0.35
    Natural
    0.33
     naturally
    0.30
    natural
    0.30
     Natural
    0.30
     natur
    0.29
     NAT
    0.27
    nat
    0.27
    grily
    0.26
    Activations Density 0.051%

    No Known Activations