© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4095
    Prev
    Next
    INDEX
    Explanations

    recent/previous

    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
    Negative Logits
    odia
    -0.20
    stdarg
    -0.20
    asso
    -0.20
    åĴĮæĶ¯æĮģ
    -0.19
    Wunused
    -0.19
    åĴĮåıijå±ķ
    -0.19
    emailer
    -0.18
    á»®
    -0.18
    ('').
    -0.18
    åĹIJ
    -0.17
    POSITIVE LOGITS
     Frag
    0.24
    previous
    0.23
     previous
    0.23
    æľīä»»ä½ķ
    0.22
     frag
    0.22
     recent
    0.22
    è¿ijæľŁ
    0.22
    çī¹æ®ĬæĥħåĨµ
    0.22
     recently
    0.21
    frag
    0.21
    Activations Density 0.340%

    No Known Activations