© 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. 4237
    Prev
    Next
    INDEX
    Explanations

    have not

    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
    亡
    -0.22
     '".
    -0.21
    trak
    -0.21
    waż
    -0.21
    panies
    -0.21
    ivitÃł
    -0.20
    amax
    -0.20
    imu
    -0.20
    esktop
    -0.19
    assis
    -0.19
    POSITIVE LOGITS
    å°ļæľª
    0.32
    é²ľ
    0.31
    è¿ĺ没æľī
    0.28
    è¿ĺæľª
    0.26
    å¾Īå°ij
    0.26
    å°ļ
    0.26
    è¿ĺ没
    0.25
    ä¸ĢçĽ´æ²¡æľī
    0.25
     haven
    0.24
     hasn
    0.24
    Activations Density 0.773%

    No Known Activations