© 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. 10188
    Prev
    Next
    INDEX
    Explanations

    making or creating things

    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
    åŃļ
    -0.09
    umed
    -0.08
    æ³½
    -0.08
    éĻįåĪ°
    -0.08
    fos
    -0.08
    æıIJæĭĶ
    -0.08
    æĬķèµĦ
    -0.08
    渡
    -0.08
    æªĢ
    -0.08
     sources
    -0.08
    POSITIVE LOGITS
    çĶ±æѤ
    0.11
    åĢŁæѤ
    0.11
    çļĦåı¯èĥ½æĢ§
    0.10
     ÙħÙĨÙĩا
    0.10
    å°±æѤ
    0.10
     بÙĪاس
    0.10
    åģļåĩº
    0.10
    以æѤ
    0.10
    åľ¨è¿Ļ
    0.09
    ÑģÑĤÑĭ
    0.09
    Activations Density 0.183%

    No Known Activations