© 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. 28114
    Prev
    Next
    INDEX
    Explanations

    making a decision

    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
     ÙĪاÙĦس
    -0.09
    æĹłç©·
    -0.08
    ulum
    -0.08
    age
    -0.08
    Anth
    -0.08
    door
    -0.08
    ground
    -0.08
    icum
    -0.08
    grounds
    -0.08
    ying
    -0.08
    POSITIVE LOGITS
    åħ±åIJĮä½ĵ
    0.12
    naire
    0.12
    åĴĮæĬĢæľ¯
    0.10
     اÙĦÙħص
    0.10
    é£ŀè·ĥ
    0.10
    nable
    0.09
    éĵ¤
    0.09
    íĺ¼
    0.09
     Abbey
    0.09
    otron
    0.08
    Activations Density 0.049%

    No Known Activations