© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    statistical significance

    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
    ='".$_
    -0.26
    tener
    -0.23
     genie
    -0.20
    ãģ¦ãģĬãĤĬãģ¾ãģĻ
    -0.20
    缶
    -0.19
    ·¸
    -0.19
     misd
    -0.19
    enny
    -0.19
     "'"
    -0.18
    violent
    -0.18
    POSITIVE LOGITS
     moderately
    0.21
     fringe
    0.20
    ronics
    0.20
     ($('#
    0.20
    æľīæīĢ
    0.19
    IRO
    0.19
    slideDown
    0.18
    ä¸īçŃīå¥ĸ
    0.18
    _Construct
    0.18
     mid
    0.18
    Activations Density 0.009%

    No Known Activations