© 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. 51130
    Prev
    Next
    INDEX
    Explanations

    proper nouns and brand names

    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
    åłª
    -0.10
    ogle
    -0.10
    姨
    -0.10
    å¹³åİŁ
    -0.10
    ç»Ļä½łä»¬
    -0.10
    artisan
    -0.10
    åıĺå¹»
    -0.09
    ç¬Ī
    -0.09
    Unc
    -0.09
    çĻ½éĵ¶
    -0.09
    POSITIVE LOGITS
    /or
    0.11
    amp
    0.10
    bows
    0.09
    深深çļĦ
    0.08
     compat
    0.08
    以åıĬ
    0.08
    å´ĩ
    0.07
    ×ij×¢
    0.07
    åıĮéĩį
    0.07
    åħ¼å®¹
    0.07
    Activations Density 0.114%

    No Known Activations