© 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. 19639
    Prev
    Next
    INDEX
    Explanations

    ending in 'ton' or 'outh'

    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
    ubb
    -0.09
     Ballard
    -0.09
     Troy
    -0.09
    çľĭä¸įæĩĤ
    -0.09
    å®ŀäºĭæ±Ĥæĺ¯
    -0.09
    éĴĪ
    -0.09
    æijĶ
    -0.08
    æ³ģ
    -0.08
    linky
    -0.08
    çīĪæĿĥæīĢæľī
    -0.08
    POSITIVE LOGITS
    åĭº
    0.10
    åī²
    0.09
    åĿĢ
    0.09
    ement
    0.08
    å¢ŀåĬłåĢ¼
    0.08
    ständ
    0.08
    åĶ¬
    0.08
    _SHARED
    0.08
    æģ¶éŃĶ
    0.08
    ä¸įç¦ģ
    0.08
    Activations Density 0.002%

    No Known Activations