© 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. 10496
    Prev
    Next
    INDEX
    Explanations

    easy as taking candy

    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
    æŀģé«ĺ
    -0.10
    è°ģçŁ¥éģĵ
    -0.10
    缸çĪ±
    -0.10
    ourses
    -0.10
    æijĬ
    -0.10
    åIJ¬çĿĢ
    -0.10
    éĺ³æĢ§
    -0.10
    æī©å»º
    -0.10
    å¸ĮæľĽå¤§å®¶
    -0.09
    亲çĪ±
    -0.09
    POSITIVE LOGITS
    寸
    0.10
    ç»ĥ
    0.09
    Åij
    0.08
    inin
    0.08
     Pot
    0.08
     mere
    0.08
    ers
    0.08
    æĺĵäºİ
    0.08
    Ord
    0.08
    ç¬ijäºĨ
    0.08
    Activations Density 0.035%

    No Known Activations