© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2123
    Prev
    Next
    INDEX
    Explanations

    genes and proteins

    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
    俱ä¹IJ
    -0.22
    ðŁ¥ĩ
    -0.22
    éĶ¦æłĩ
    -0.22
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.21
     ëĮĢíķĺìŬ
    -0.21
    çĽijåIJ¬é¡µéĿ¢
    -0.21
    为æĬĵ
    -0.20
    éĩĩçŁ¿çŃī
    -0.20
    koneksi
    -0.20
    çĪ±å¥ĩ
    -0.20
    POSITIVE LOGITS
     involved
    0.27
    å½±åĵį
    0.25
    åıĤä¸İ
    0.24
    è´Ł
    0.22
    æݧåĪ¶
    0.22
    缴æݥ影åĵį
    0.21
    æ¶īåıĬåĪ°
    0.21
     control
    0.21
    eyer
    0.20
    ç³ģ
    0.20
    Activations Density 0.709%

    No Known Activations