© 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. 9040
    Prev
    Next
    INDEX
    Explanations

    has been

    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
    _MAKE
    -0.10
    DEFINED
    -0.10
    è¡£
    -0.09
    æī¿åĬŀ
    -0.09
     ÑģмÑĭÑģл
    -0.08
    bonus
    -0.08
    promise
    -0.08
    .scalar
    -0.08
    chnitt
    -0.08
    æĦıä¹ī
    -0.08
    POSITIVE LOGITS
    ä¸Ģè´¯
    0.10
    è°¨
    0.10
    è¬
    0.09
    é«ĺ度éĩįè§Ĩ
    0.09
    å§ĭç»ĪåĿļæĮģ
    0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.09
    åħ¥å¸Ĥ
    0.09
    iglia
    0.09
    èĩªæľī
    0.09
    èĩ´åĬĽäºİ
    0.08
    Activations Density 0.078%

    No Known Activations