© 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. 46696
    Prev
    Next
    INDEX
    Explanations

    internal biases

    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
    è¾ĵç»Ļ
    -0.23
    oriously
    -0.21
    ItemAt
    -0.20
    åĶĨ
    -0.20
    ensi
    -0.20
     cougar
    -0.19
    EXTERN
    -0.18
    è¾į
    -0.18
    beck
    -0.18
    recio
    -0.17
    POSITIVE LOGITS
     ×Ķ×ķ×ĵ
    0.23
    ;element
    0.23
     undermin
    0.22
    ivist
    0.22
    xico
    0.21
     Belgi
    0.20
    .bunifuFlatButton
    0.20
    rades
    0.20
    Mono
    0.20
    HttpStatus
    0.20
    Activations Density 0.001%

    No Known Activations