© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    tap

    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
     Dumpster
    -0.25
     Interracial
    -0.23
    줬
    -0.23
    uem
    -0.22
     ActionTypes
    -0.22
    }}>↵
    -0.22
    macen
    -0.22
    aight
    -0.22
    .DecimalField
    -0.21
     èĩªåĬ¨çĶŁæĪIJ
    -0.21
    POSITIVE LOGITS
    ä¼ģä¸ļ管çIJĨ
    0.20
     typeid
    0.20
     Bun
    0.19
     tapped
    0.19
     tap
    0.19
    ettings
    0.19
    ruise
    0.18
    Ħ
    0.18
    .Align
    0.18
    _todo
    0.18
    Activations Density 0.006%

    No Known Activations