© 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. 20753
    Prev
    Next
    INDEX
    Explanations

    endocrine disruptors

    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
    èĪªå¤©
    -0.10
    缯
    -0.10
    对æĬĹ
    -0.10
    æ²¹çĶ°
    -0.09
     !***
    -0.09
    缴è§Ĥ
    -0.09
    åħ³äºİæĪij们
    -0.09
    ä¸Ģèīĺ
    -0.09
    æ²¹èĦĤ
    -0.09
    åĩłçĤ¹
    -0.09
    POSITIVE LOGITS
    ually
    0.09
    æ©IJ
    0.09
     Tune
    0.09
    ulong
    0.09
    bis
    0.09
    éļĶ
    0.09
     Mang
    0.08
    zes
    0.08
    _OID
    0.08
     bis
    0.08
    Activations Density 0.011%

    No Known Activations