© 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. 9109
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĤ¼
    -0.10
    å¤Ļ
    -0.09
    çĭ¬
    -0.09
    arton
    -0.09
    å¿ĥè¡Ģ管
    -0.09
    ë³ij
    -0.08
    殿åłĤ
    -0.08
    èijŃ
    -0.08
    ç¼ĺåĪĨ
    -0.08
    éģĹ产
    -0.08
    POSITIVE LOGITS
    没æĶ¶
    0.09
    æīij
    0.09
    éĹ¾
    0.09
    èİł
    0.09
    æ¸ħéĻ¤
    0.09
    å®īåºĨ
    0.09
    ä¸Ĭå®ĺ
    0.08
    ç½ļ
    0.08
    orde
    0.08
    urette
    0.08
    Activations Density 0.044%

    No Known Activations