© 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. 19578
    Prev
    Next
    INDEX
    Explanations

    plated, nonferrous, copper/nickel

    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
    å·´å·´
    -0.10
    éĢł
    -0.10
    åĹ¾
    -0.09
    ijkl
    -0.09
    ëł¹
    -0.09
    pta
    -0.09
     slur
    -0.09
     peri
    -0.09
    irma
    -0.08
    穹
    -0.08
    POSITIVE LOGITS
    éĩijæ²Ļ
    0.10
    ãģĵãģ¨ãģĮãģĤãĤĭ
    0.08
    æµ´
    0.08
    éķ¶
    0.08
     thi
    0.08
     pare
    0.08
    ì°°
    0.08
    pare
    0.07
     Bronx
    0.07
    à¹Ģà¸ģร
    0.07
    Activations Density 0.063%

    No Known Activations