© 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. 4178
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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
    çıħ
    -0.23
    ;break
    -0.22
    smouth
    -0.20
    Active
    -0.20
    _FB
    -0.20
    /↵↵↵↵
    -0.20
    cen
    -0.19
     active
    -0.19
    åĥŃ
    -0.19
    onestly
    -0.19
    POSITIVE LOGITS
     )↵↵↵↵↵↵↵↵
    0.22
    ertools
    0.20
    urrenc
    0.20
     comentarios
    0.19
     Newest
    0.19
    çĶ
    0.18
     shemale
    0.18
    &);↵↵
    0.18
     ApiController
    0.18
    äºĨ好å¤ļ
    0.18
    Activations Density 0.001%

    No Known Activations