© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    code use

    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
     Clintons
    -0.32
     (~(
    -0.31
     Kardash
    -0.29
     enthus
    -0.28
    sist
    -0.28
    ,strlen
    -0.28
     Erotic
    -0.28
    -NLS
    -0.27
    ,{"
    -0.26
     masturbating
    -0.26
    POSITIVE LOGITS
     inside
    0.23
    utherland
    0.22
    ESSAGE
    0.21
    æļĮ
    0.21
    å¿Ŀ
    0.21
    å¨ī
    0.21
     directly
    0.21
    æĻ¯å¾·
    0.20
     use
    0.20
    çĿ½
    0.20
    Activations Density 6.523%

    No Known Activations