© 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. 46117
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    //*[
    -0.21
    NotAllowed
    -0.20
    icos
    -0.20
     Waterproof
    -0.19
     üz
    -0.19
    коло
    -0.18
     damp
    -0.18
    patibility
    -0.18
    æĺŁ
    -0.18
     loophole
    -0.17
    POSITIVE LOGITS
    âĺ°
    0.21
     Naz
    0.20
    amient
    0.19
    avo
    0.19
    leh
    0.19
    olis
    0.19
    пеÑĢедаÑĩ
    0.19
    Disappear
    0.19
    bow
    0.19
    styleType
    0.18
    Activations Density 0.000%

    No Known Activations