© 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. 370
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    游æĪıæĬĢå·§
    -0.28
     IonicPage
    -0.26
    gnore
    -0.25
    åij£
    -0.25
    zerbai
    -0.24
    纪å§Ķ书记
    -0.24
     èĭ¥è¦ģ
    -0.23
    å§ĭ建
    -0.23
    OffsetTable
    -0.22
     getpid
    -0.22
    POSITIVE LOGITS
    ä»ĸå¦Ī
    0.23
    åĸij
    0.22
    nowrap
    0.21
    \_
    0.21
    zcze
    0.20
    mojom
    0.20
     costa
    0.20
    è¦ģ好好
    0.20
     pobliżu
    0.20
    elaide
    0.20
    Activations Density 3.892%

    No Known Activations