© 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-CHAT-65K
    7. 45905
    Prev
    Next
    INDEX
    Explanations

    delimited text

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evity
    -0.23
    mdat
    -0.23
    åľ¨ä¼łå¥ĩ
    -0.23
    :white
    -0.22
    aghetti
    -0.21
    úsqueda
    -0.21
    inoa
    -0.21
    nets
    -0.21
    ÅĤuż
    -0.20
    ificate
    -0.20
    POSITIVE LOGITS
     bada
    0.24
     consc
    0.22
     porno
    0.22
    ä¸įè§ģäºĨ
    0.21
    åıijåŀĭ
    0.21
     noe
    0.20
     maç
    0.20
     servi
    0.20
    æķ²
    0.20
    个乡éķĩ
    0.20
    Activations Density 0.003%

    No Known Activations