© 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. 3091
    Prev
    Next
    INDEX
    Explanations

    specific references

    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
    metic
    -0.27
    oplan
    -0.25
    ampionship
    -0.24
    yms
    -0.24
     follando
    -0.23
    iconductor
    -0.22
    antro
    -0.22
    oriously
    -0.22
    ampie
    -0.21
    _icall
    -0.21
    POSITIVE LOGITS
    æĬ¬å¤´
    0.20
     nya
    0.19
    å¾Ĺå¤ļ
    0.19
     gross
    0.19
     paddingLeft
    0.19
    oux
    0.19
    åIJİåĨį
    0.18
    豪车
    0.18
     perÃŃ
    0.17
    çĥĪ
    0.17
    Activations Density 0.001%

    No Known Activations