© 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-65K
    7. 2678
    Prev
    Next
    INDEX
    Explanations

    named entities and numbers

    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
    )(__
    -0.24
    )))));↵
    -0.24
    :animated
    -0.23
    =Value
    -0.23
    ORED
    -0.23
    .Millisecond
    -0.23
    :frame
    -0.22
    .SpringBootApplication
    -0.22
    iá»ĩu
    -0.21
    åĦĩ
    -0.21
    POSITIVE LOGITS
    çĿ¥
    0.20
     Sch
    0.19
     sulla
    0.18
    ç´
    0.18
     Romney
    0.18
    Ctx
    0.18
    Reply
    0.18
     typingsJapgolly
    0.17
    abet
    0.17
     Ciudad
    0.17
    Activations Density 0.001%

    No Known Activations