© 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. 61909
    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
    etri
    -0.10
    çģ¯åħī
    -0.09
    .override
    -0.08
    ior
    -0.08
    ä¹ĭåĬ¿
    -0.08
    Ùģا
    -0.08
    YouTube
    -0.08
    éĹ²ç½®
    -0.08
    寮
    -0.08
    èĹ
    -0.08
    POSITIVE LOGITS
    ujet
    0.10
    иÑĨÑĭ
    0.09
    (handles
    0.09
    redni
    0.09
    æķ´ä¸ª
    0.09
    omatic
    0.09
    åѦ龸
    0.09
    æī¼
    0.09
    å°ıçĭĹ
    0.08
    éģį
    0.08
    Activations Density 0.000%

    No Known Activations