© 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. 46215
    Prev
    Next
    INDEX
    Explanations

    also

    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
    æī¿æĭħ责任
    -0.21
    	freopen
    -0.21
    elia
    -0.19
    '].$
    -0.19
     verschill
    -0.19
    çĶļèĩ³
    -0.19
    arme
    -0.18
    _reordered
    -0.18
    -collapse
    -0.18
    лев
    -0.18
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.21
    .portal
    0.20
    ãĤŃãĥ³
    0.20
    doÄŁan
    0.19
    Endian
    0.19
     kako
    0.19
    orpor
    0.19
    eslint
    0.19
     ><?
    0.19
    -ci
    0.19
    Activations Density 0.028%

    No Known Activations