© 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. 3915
    Prev
    Next
    INDEX
    Explanations

    uniform, consistent

    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
     direct
    -0.20
    keterangan
    -0.19
     comple
    -0.19
    ðŁĵIJ
    -0.19
     indirect
    -0.19
    ifen
    -0.18
    ]});↵
    -0.18
    ç«ĭä½ĵ
    -0.18
    éĹ´æİ¥
    -0.18
     masturbating
    -0.17
    POSITIVE LOGITS
    绣ä¸Ģ
    0.70
     uniform
    0.59
    ä¸Ģèĩ´
    0.55
    åħ±åIJĮ
    0.52
    uniform
    0.49
    ä¸Ģèĩ´æĢ§
    0.49
     shared
    0.47
     consistent
    0.47
    绣
    0.46
    Uniform
    0.45
    Activations Density 0.974%

    No Known Activations