© 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. 4279
    Prev
    Next
    INDEX
    Explanations

    abstract qualities

    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
    åħ¸åŀĭ
    -0.26
     typical
    -0.24
    :focus
    -0.21
    常è§ģ
    -0.21
    classic
    -0.21
     Typical
    -0.21
     classic
    -0.20
    åħ¸åŀĭçļĦ
    -0.20
    ypical
    -0.20
     INCIDENT
    -0.19
    POSITIVE LOGITS
    forgettable
    0.26
    æĺ¯ä¸Ģ项
    0.25
    å°±ç»Ļ大家
    0.24
     FindObjectOfType
    0.24
    ä¸ĢéŨ
    0.23
    thinkable
    0.23
    Mathf
    0.23
    ä½ľä¸ºä¸Ģç§į
    0.21
    ä¸İåħ¶ä»ĸ
    0.20
    ',...↵
    0.20
    Activations Density 0.882%

    No Known Activations