© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2175
    Prev
    Next
    INDEX
    Explanations

    identify field names

    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/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "description
    -0.21
    CGSize
    -0.20
     onBindViewHolder
    -0.18
    ä¸įçĶ±
    -0.18
    моÑĢ
    -0.18
    mouseenter
    -0.18
    adan
    -0.18
    abis
    -0.17
    quoise
    -0.17
    ãģĶåĪ©çĶ¨
    -0.17
    POSITIVE LOGITS
    ç¼ĸåı·
    0.40
     id
    0.36
    åIJįåŃĹ
    0.34
    id
    0.33
    åIJį称
    0.33
    çļĦåIJįåŃĹ
    0.32
     name
    0.31
    .id
    0.31
    _id
    0.30
    对åħ¶çľŁå®ŀ
    0.29
    Activations Density 0.557%

    No Known Activations