© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49146
    Prev
    Next
    INDEX
    Explanations

    flashcard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    èĨĽ
    -0.10
    ä¸įæĺ¯ä¸Ģ个
    -0.10
    髯
    -0.10
    offsetof
    -0.10
    èŁĴ
    -0.10
    éļĪ
    -0.09
    linkplain
    -0.09
    å¦ĤæĦı
    -0.09
    åĺĮ
    -0.09
    涤
    -0.09
    POSITIVE LOGITS
     cards
    0.12
    åį¡çīĩ
    0.11
    Memory
    0.08
    åħ´
    0.08
    cards
    0.08
    泡
    0.08
     hiring
    0.08
     abandonment
    0.08
    æģŃ
    0.08
     fich
    0.08
    Activations Density 0.012%

    No Known Activations