© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    submit

    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
    å¾ħéģĩ
    -0.24
    ntax
    -0.24
    åıijæĶ¾
    -0.22
    oreal
    -0.21
    aryana
    -0.20
    itung
    -0.19
    _PREVIEW
    -0.19
    wyn
    -0.19
    otonin
    -0.19
    ést
    -0.18
    POSITIVE LOGITS
     submission
    0.34
     submitted
    0.31
     submissions
    0.30
    æıIJ交
    0.27
     submitting
    0.27
    submitted
    0.27
     Submit
    0.27
    submit
    0.27
     submit
    0.26
     Submitted
    0.25
    Activations Density 0.463%

    No Known Activations