© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    programming license metadata

    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
     recent
    -0.29
    åħ¨èµĦåŃIJ
    -0.27
    (ConfigurationManager
    -0.26
    å§ĭ建äºİ
    -0.25
    è¿ijå¹´æĿ¥
    -0.25
    ä¸Ĭä¸ĸ纪
    -0.24
    è¿ijæľŁ
    -0.24
    å¤ļå¹´æĿ¥
    -0.24
    è¿ijæĹ¥
    -0.23
    åĩłå¹´åīį
    -0.23
    POSITIVE LOGITS
     brun
    0.22
     MainAxisAlignment
    0.21
     Wich
    0.21
    éĩįçĤ¹å·¥ä½ľ
    0.20
    ledo
    0.20
    ä¸ĭéĿ¢æĺ¯å°ı
    0.19
     scape
    0.19
     swinger
    0.19
     swingers
    0.18
    ãĥµ
    0.18
    Activations Density 1.495%

    No Known Activations