© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52173
    Prev
    Next
    INDEX
    Explanations

    economy

    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
    ordin
    -0.10
    cede
    -0.09
    æĶ¿æĿĥ
    -0.09
    locales
    -0.09
    åĻ¨
    -0.09
    bred
    -0.09
    -million
    -0.09
    _DM
    -0.09
    äººæł¼
    -0.08
    èĩ¾
    -0.08
    POSITIVE LOGITS
    çĬ¶åĨµ
    0.09
    æŃ£å¤Ħäºİ
    0.09
    å½¢åĬ¿
    0.08
     Pall
    0.08
    æķ´ä½ĵ
    0.08
    -wide
    0.08
    amic
    0.08
    èĽŃ
    0.08
    æĻ®æŁ¥
    0.08
    çİ°çĬ¶
    0.08
    Activations Density 0.009%

    No Known Activations