© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11956
    Prev
    Next
    INDEX
    Explanations

    drugs, religion, communities

    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
     jur
    -0.09
    ç¿ħ
    -0.09
    ibr
    -0.09
    åĭ¾
    -0.09
     weights
    -0.08
    æĵħéķ¿
    -0.08
    tick
    -0.08
    æīŃ
    -0.08
    ä»ħ代表
    -0.08
    é¥ķ
    -0.08
    POSITIVE LOGITS
    æľįçĶ¨
    0.10
     Tucker
    0.09
    éĿĴæĺ¥
    0.09
    é¢Ĩ导人
    0.09
    rese
    0.09
    åįĬå¤ľ
    0.09
    ANGLES
    0.09
     trải
    0.09
     exper
    0.09
    ncia
    0.09
    Activations Density 0.080%

    No Known Activations