© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46734
    Prev
    Next
    INDEX
    Explanations

    code or structure

    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
    íĶĦë¡ľê·¸
    -0.28
     ($('#
    -0.28
     ($("#
    -0.27
     Raqqa
    -0.25
     sophistic
    -0.25
    ç»
    -0.25
    arendra
    -0.25
    phalt
    -0.24
    oriously
    -0.24
    stants
    -0.23
    POSITIVE LOGITS
    åĨ
    0.22
    翳
    0.22
    è°ij
    0.20
     upd
    0.20
     mel
    0.19
    enne
    0.19
     add
    0.19
     as
    0.19
    [DllImport
    0.19
    @show
    0.19
    Activations Density 0.001%

    No Known Activations