© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3779
    Prev
    Next
    INDEX
    Explanations

    period

    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
    没åħ³ç³»
    -0.24
    以åħį
    -0.24
    严éĩįå½±åĵį
    -0.23
    幸好
    -0.21
    ç®ĹäºĨ
    -0.21
    \Service
    -0.21
    以便
    -0.20
     requestOptions
    -0.20
    好ä¸į容æĺĵ
    -0.20
     Thankfully
    -0.20
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.33
    åĶ¯ä¸ĢçļĦ
    0.32
    ãģŁãģłãģĹ
    0.31
     ëĭ¤ë§Į
    0.31
     sogar
    0.30
    å°¤åħ¶æĺ¯
    0.30
    å°¤åħ¶æĺ¯åľ¨
    0.30
    缺çĤ¹
    0.30
     downside
    0.30
    åı¯æĥľ
    0.30
    Activations Density 0.607%

    No Known Activations