© 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. 45805
    Prev
    Next
    INDEX
    Explanations

    code related

    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
    %;"
    -0.24
    FormsModule
    -0.23
    _refl
    -0.23
    andalone
    -0.23
     AppComponent
    -0.22
    .IsNullOr
    -0.22
    //**↵
    -0.22
     zar
    -0.22
    ãĥµ
    -0.21
    èĭ«
    -0.21
    POSITIVE LOGITS
    .minLength
    0.21
     Maher
    0.20
    ɹ
    0.20
    räg
    0.19
    ponce
    0.18
    éģĩ
    0.18
    _viewer
    0.18
    çĨł
    0.18
    è¤Ĥ
    0.18
     high
    0.17
    Activations Density 0.120%

    No Known Activations