© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36175
    Prev
    Next
    INDEX
    Explanations

    household tasks and appliances

    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
     Bark
    -0.10
    èĭ
    -0.09
    çĶŁåij½åĬĽ
    -0.09
     Pret
    -0.08
    æĢ»çļĦ
    -0.08
    pret
    -0.08
    NOP
    -0.08
    æĸĩåŃĹ
    -0.08
    çĮĹ
    -0.08
    è£ģ
    -0.08
    POSITIVE LOGITS
    家åĬ¡
    0.11
     household
    0.10
    çĶŁæ´»ä¸Ń
    0.10
    çĶ¨åĵģ
    0.10
    åĴĮ个人
    0.09
    åݨ
    0.09
     Routine
    0.09
    èĢģåħ¬
    0.09
     Bru
    0.09
    沪
    0.09
    Activations Density 0.067%

    No Known Activations