© 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. 393
    Prev
    Next
    INDEX
    Explanations

    music releases

    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
    çŀł
    -0.28
     Erotic
    -0.27
     Erot
    -0.26
     felon
    -0.26
     Kardash
    -0.26
    纰
    -0.26
     libertine
    -0.24
     tantra
    -0.24
    éĢłåģĩ
    -0.24
    è¯ĭ
    -0.24
    POSITIVE LOGITS
    建档ç«ĭ
    0.27
    åıijè¡Į
    0.27
    主æīĵ
    0.25
    âĻ¯
    0.25
    HideInInspector
    0.25
    ($)
    0.24
    æĢ§ä»·
    0.24
    åĹ¥
    0.23
    -instagram
    0.23
    ç´łæĻ´
    0.23
    Activations Density 2.461%

    No Known Activations