© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    narrative descriptions

    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
     libertine
    -0.42
     vö
    -0.38
     libertin
    -0.33
    为äºĨæĽ´å¥½
    -0.30
     bigot
    -0.29
     egreg
    -0.29
     tantra
    -0.29
     erotica
    -0.28
     blat
    -0.28
     fick
    -0.28
    POSITIVE LOGITS
    ãİŀ
    0.33
    åĵªå®¶å¥½
    0.29
    :'.$
    0.28
    âĦħ
    0.28
    并ä¸įæĺ¯å¾Ī
    0.28
    /MPL
    0.26
    нибÑĥдÑĮ
    0.26
     practition
    0.26
    âĶ¬
    0.25
    ":-
    0.25
    Activations Density 8.195%

    No Known Activations