© 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. 18244
    Prev
    Next
    INDEX
    Explanations

    numbers, money, scores

    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
    Ñĥни
    -0.08
    è°¨
    -0.08
    fen
    -0.08
    æĩĴ
    -0.08
    ukt
    -0.08
    åı²ä¸ĬæľĢ
    -0.08
    çļĦä½ľåĵģ
    -0.07
    第ä¸Ģ个
    -0.07
    çļĦ游æĪı
    -0.07
    å°ıçĭĹ
    -0.07
    POSITIVE LOGITS
    åIJĮæĥħ
    0.09
    ä»Ģä¹Īéĥ½
    0.09
    uzz
    0.09
    äºĶæĺŁ
    0.09
    éĥĩ
    0.08
    çī²
    0.08
    èī¯
    0.08
    èķ²
    0.08
    çĶij
    0.08
     ksztaÅĤt
    0.08
    Activations Density 0.078%

    No Known Activations