© 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. 62443
    Prev
    Next
    INDEX
    Explanations

    beginning or appearance of something

    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
    çijĦ
    -0.10
    åģľè½¦
    -0.09
     Harr
    -0.09
    ees
    -0.09
    ãģªãģijãĤĮãģ°
    -0.08
    aru
    -0.08
    ãģª
    -0.08
    OPS
    -0.08
    é²Ķ
    -0.08
    owane
    -0.08
    POSITIVE LOGITS
    æ±Łæ¹ĸ
    0.10
     Dah
    0.09
    å¹ķ
    0.09
    å®ī稳
    0.08
    ilde
    0.08
    æļ´
    0.08
    å¿ħçĦ¶
    0.08
    é£İéĩĩ
    0.08
    Ñīа
    0.08
    ijd
    0.08
    Activations Density 0.047%

    No Known Activations