© 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. 33991
    Prev
    Next
    INDEX
    Explanations

    luxury, comfort, cozy

    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
    æı½
    -0.10
    åĴ±
    -0.09
    å§Ĭ妹
    -0.09
    åħĪæĺ¯
    -0.09
    åŃĺæ´»
    -0.08
    æĭĽ
    -0.08
    vented
    -0.08
    æīĪ
    -0.08
    orpion
    -0.08
    å¾ĹæĦı
    -0.08
    POSITIVE LOGITS
    ä¸į失
    0.10
    械
    0.09
    æĽ·
    0.08
    容è²Į
    0.08
    çļĦç«ŀäºī
    0.08
    æİĤ
    0.08
     Alic
    0.08
    èĬĤ
    0.08
    æĭ¦
    0.08
    åīį线
    0.08
    Activations Density 0.012%

    No Known Activations