© 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. 4147
    Prev
    Next
    INDEX
    Explanations

    nothing

    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
     Dems
    -0.22
    []>↵
    -0.21
    å´
    -0.19
    ".↵↵↵↵
    -0.19
     IconData
    -0.18
    _wire
    -0.17
    VertexAttribArray
    -0.17
    eday
    -0.17
    stakes
    -0.17
    FormGroup
    -0.17
    POSITIVE LOGITS
     nothing
    0.35
    nothing
    0.31
    (){}↵
    0.30
     Nothing
    0.29
    (){}↵↵
    0.27
     rien
    0.24
    ][/
    0.24
     ниÑĩего
    0.24
     pass
    0.23
    Nothing
    0.23
    Activations Density 0.375%

    No Known Activations