© 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. 51907
    Prev
    Next
    INDEX
    Explanations

    e-commerce retailers and branded companies

    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
    罩
    -0.09
    ilians
    -0.08
     Nancy
    -0.08
    çµ®
    -0.08
    çļĦåıijçĶŁ
    -0.08
    usan
    -0.08
    饽
    -0.07
    èµĸ
    -0.07
    tpl
    -0.07
    THING
    -0.07
    POSITIVE LOGITS
    åı°ä¸Ĭ
    0.09
    lijah
    0.09
    _PB
    0.09
     Tal
    0.09
    دائ
    0.09
    çĤŃ
    0.09
    çĹ¼
    0.08
    æµļ
    0.08
    è¿ĻéĩĮæľī
    0.08
    å¼łæī¬
    0.08
    Activations Density 0.004%

    No Known Activations