© 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. 46023
    Prev
    Next
    INDEX
    Explanations

    AI assistant prompts

    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
    ième
    -0.21
    .Rollback
    -0.20
    _cuda
    -0.20
    ụ
    -0.19
    .trailingAnchor
    -0.18
     jeste
    -0.18
    stdarg
    -0.18
    xa
    -0.18
    strtotime
    -0.18
    çł¹
    -0.18
    POSITIVE LOGITS
    SizePolicy
    0.27
    ystore
    0.23
    ughters
    0.21
     Joi
    0.20
     èĩªåĬ¨çĶŁæĪIJ
    0.20
    .ManyToMany
    0.19
    pson
    0.19
    plx
    0.19
    -initialized
    0.19
    Projected
    0.19
    Activations Density 0.001%

    No Known Activations