© 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. 7167
    Prev
    Next
    INDEX
    Explanations

    dog/puppy/pig/rat/monkey behavior

    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
    åľºæīĢ
    -0.09
    大è¡Ĺ
    -0.09
    ä¸ĭæīĭ
    -0.09
    äºĨä¸Ģéģį
    -0.08
    ones
    -0.08
    马æĭī
    -0.08
    ArrayOf
    -0.08
    å·¥ä½ľä¸Ń
    -0.08
    è¿ŀäºij
    -0.08
    Locker
    -0.08
    POSITIVE LOGITS
    åĢij
    0.11
    群
    0.10
    å°¤åħ¶æĺ¯
    0.10
    ä¹ĭ家
    0.09
    çļĦçŁ¥è¯Ĩ
    0.09
    们
    0.09
    çī¹åĪ«æĺ¯
    0.09
    ãģŁãģ¡
    0.09
    们çļĦ
    0.09
    åıĬåħ¶
    0.09
    Activations Density 0.168%

    No Known Activations