© 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. 4003
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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
    EMENT
    -0.21
    ();++
    -0.21
    éŃĩ
    -0.20
    objectId
    -0.19
    onent
    -0.19
    <?↵
    -0.19
    .toHexString
    -0.19
    kü
    -0.18
    "path
    -0.18
    >>()
    -0.18
    POSITIVE LOGITS
    iros
    0.21
    gages
    0.21
     UIAlert
    0.20
     "(\<
    0.20
     èĭ¥è¦ģ
    0.20
    -produ
    0.19
     scrim
    0.19
    nda
    0.19
    ç¦ļ
    0.19
     masturb
    0.19
    Activations Density 0.010%

    No Known Activations