© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
    /Dk
    -0.29
    ç¡ķ士çłĶ究
    -0.27
    peater
    -0.21
    dealloc
    -0.21
    .toCharArray
    -0.20
    .surname
    -0.20
    }><
    -0.20
    /epl
    -0.20
    TAG
    -0.20
    loquent
    -0.19
    POSITIVE LOGITS
    ltre
    0.27
    owego
    0.24
    ç¾İåªĴ
    0.23
     Prostit
    0.22
    导èĪª
    0.22
    ÎIJ
    0.21
    .LogWarning
    0.20
    orsi
    0.20
    ="{!!
    0.20
     toc
    0.20
    Activations Density 0.789%

    No Known Activations