© 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. 32623
    Prev
    Next
    INDEX
    Explanations

    positive or negative outcomes

    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
    jack
    -0.09
    éĺ¶æ®µæĢ§
    -0.09
    “He
    -0.09
    精彩
    -0.08
    è¿Ļæł·æīįèĥ½
    -0.08
    å«Įçĸij
    -0.08
     Rams
    -0.08
    iers
    -0.08
    好åIJĹ
    -0.08
    å»ĵ
    -0.08
    POSITIVE LOGITS
    åĽŀå¿Ĩ
    0.10
    å¼Ģ端
    0.09
     обÑĢазом
    0.09
    åĵģè´¨
    0.09
    æĶ¹è¿Ľ
    0.09
    ä¹ĭä½ľ
    0.09
    ä¸įäºĨ
    0.08
    _sv
    0.08
    äºĨæĪijçļĦ
    0.08
    åħ¨é¢Ŀ
    0.08
    Activations Density 0.014%

    No Known Activations