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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 645
    Prev
    Next
    INDEX
    Explanations

    mathematical expression

    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
     GANG
    -0.35
    ðŁĵIJ
    -0.34
    âļĹ
    -0.33
    âĨ¾
    -0.31
    /MIT
    -0.28
     Erectile
    -0.28
     dumpsters
    -0.27
     BuzzFeed
    -0.27
     Girlfriend
    -0.26
     ++)
    -0.26
    POSITIVE LOGITS
     expression
    0.31
     expressions
    0.31
     formula
    0.27
    忽çķ¥äºĨ
    0.26
    åħ¶å®ĥéĹ®é¢ĺ
    0.25
    åijĽ
    0.25
    å¦Ĥæŀľçݩ家
    0.25
    çĭ¬ä¸Ģ
    0.24
     straightforward
    0.24
     simpl
    0.24
    Activations Density 0.700%

    No Known Activations