© 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. 4015
    Prev
    Next
    INDEX
    Explanations

    technical items and data

    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
    tero
    -0.22
    ','"+
    -0.21
    ião
    -0.21
    enze
    -0.21
    )((((
    -0.19
    egra
    -0.19
    woke
    -0.19
     stamped
    -0.19
    å®ŀäºĭæ±Ĥ
    -0.19
    finity
    -0.19
    POSITIVE LOGITS
     &);↵
    0.23
    (UnityEngine
    0.20
     FixedUpdate
    0.20
    odesk
    0.20
    ($('<
    0.19
    \Carbon
    0.19
    _KeyDown
    0.19
    (jsonPath
    0.19
    .HttpServletResponse
    0.19
    customerId
    0.18
    Activations Density 0.001%

    No Known Activations